debug-investigate

name	debug-investigate
description	[Fix & Debug] Use when bugfix workflow reaches debug step.

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Prefer the plan-hard skill for planning guidance in this Codex mirror.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex does not receive Claude hook-based doc injection. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec/test-case planning or TC mapping: feature-docs-reference.md
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: Investigate, identify root cause with file:line evidence. Investigation-only — hand off to $fix for implementation.

Workflow:

1. Classify — Detect bug scenario type (Phase 0) → route to specialized agent
2. Reproduce — Confirm expected vs actual with evidence
3. Hypothesize — Form 2-3 ranked theories
4. Trace — Follow code paths; collect file:line proof per hypothesis
5. Confirm — Single root cause explains ALL symptoms
6. Validate — Fresh Eyes round 2 before declaring confirmed
7. Report — Confidence-tagged finding + hand off to $fix

Key Rules:

• NEVER patch symptoms — trace full call chain, fix at owning layer
• NEVER report root cause without file:line evidence
• NEVER declare confirmed root cause after Round 1 alone (Fresh Eyes required)
• Output: confirmed root cause OR "hypothesis, not confirmed" + evidence gaps

Phase 0: Classify Bug Scenario (BLOCKING — Do Before ANY Investigation)

Think: What type of failure is this? Classification routes to the right agent and determines which evidence matters most.

Bug Type	Signals	Specialized Agent
Frontend UI / rendering	Console errors, visual regression, component state	debugger
Backend logic / data	Wrong API response, data corruption, validation failure	debugger
Cross-service / message bus	Events not propagating, consumer failures, sync lag	debugger + graph trace MANDATORY
Performance / memory	Slow queries, OOM, N+1, unbounded result sets	performance-optimizer
Security / auth	Access denied, token issues, permission bypass	security-auditor

Cross-service bugs: Run graph trace FIRST — grep alone misses implicit bus connections. OOM / memory exhaustion: Check row COUNT before row SIZE. Unbounded query loading thousands of records is the more common cause. Triage: (1) missing DB-level filter? (2) excessive row size?

Debug Mindset (NON-NEGOTIABLE)

Skeptical. Sequential. Every claim needs traced proof, confidence >80%.

• NEVER assume first hypothesis correct — verify with actual code traces
• Every root cause claim MUST include file:line evidence
• Cannot prove root cause → state "hypothesis, not confirmed"
• Challenge assumptions: "Is this really the cause?" → trace actual execution path
• Challenge completeness: "Other contributing factors?" → check related code paths

Confidence & Evidence Gate

MUST ATTENTION declare Confidence: X% + evidence list + file:line proof for EVERY claim.

Confidence	Meaning	Action
95-100%	Full trace verified	Report as confirmed root cause
80-94%	Main path verified, edge cases uncertain	Report with caveats
60-79%	Partial trace	Report as hypothesis
<60%	Insufficient evidence	DO NOT report — gather more evidence

Investigation Dimensions

Reason through each dimension — state what fails if weak, then apply with evidence.

Dim 1: Reproduce

Think: What exact conditions trigger this? Data state? User action? Timing? Environment delta?

• Confirm issue exists with evidence (error message, stack trace, screenshot)
• Identify trigger: user action, data state, timing, env difference

Dim 2: Hypothesize

Think: Given symptoms, what are the most plausible failure modes? What would confirm vs contradict each?

• Form 2-3 theories ranked by likelihood
• Note evidence needed to confirm/contradict each theory before investigating

Dim 3: Trace

Think: Where does bad state ENTER the system — not where it CRASHES? Which layer owns this invariant?

• Find entry point (API, UI, job, event)
• Follow through handlers/services/transformations
• Check error handling paths
• Collect file:line evidence per hypothesis
• Use graph trace for implicit connections (event handlers, bus consumers)

Dim 4: Confirm

Think: Does this root cause explain ALL symptoms? Are there bypass paths that skip the fix point?

• Match evidence to single root cause
• Verify root cause explains ALL observed symptoms
• Check secondary contributing factors
• Verify no bypass paths (direct construction, clone/spread without re-validation, mutations outside model layer)

Dim 5: Report

• Output: confirmed root cause + evidence chain
• Include: affected files, data flow summary, fix recommendation
• Hand off to $fix for implementation

Dependency Tracing (MANDATORY when graph.db exists)

MUST ATTENTION use structural queries — graph reveals ALL callers/consumers grep misses.

# Who calls the buggy function
python .claude/scripts/code_graph query callers_of <function> --json

# Who imports the buggy module
python .claude/scripts/code_graph query importers_of <file> --json

# What tests exist
python .claude/scripts/code_graph query tests_for <function> --json

# Full upstream + downstream context
python .claude/scripts/code_graph trace <suspect-file> --direction both --json

# Callers only (find all trigger points)
python .claude/scripts/code_graph trace <suspect-file> --direction upstream --json

Graph reveals implicit connections (MESSAGE_BUS, event handlers) that propagate issues across services — invisible to grep.

Root Cause Validation (Fresh Eyes Protocol)

NEVER declare confirmed root cause after Round 1 alone. Main agent rationalizes its own findings — a zero-memory sub-agent catches what main agent dismissed.

Round 1 (main agent): Identify root cause + full evidence chain. Write findings to report file.

Round 2 (fresh debugger sub-agent, zero memory of Round 1): Spawn with:

• Suspected root cause statement
• All file:line evidence collected
• Ask: "Does this evidence conclusively prove the stated root cause, or are there gaps?"

Decision:

• Sub-agent CONFIRMS → declare confirmed, proceed to $fix
• Sub-agent finds GAPS → collect additional evidence, repeat
• 2 rounds without confirmation → STOP, escalate to user via a direct user question

⚠️ MANDATORY: Post-Fix Verification

After $fix applies changes, $prove-fix MUST be run — builds code proof traces per change with confidence scores. Non-negotiable in all fix workflows.

Anti-Rationalization (Red Flags)

Evasion	Rebuttal
"I see the problem, let me fix it"	Symptoms ≠ root cause. Investigate first.
"Quick fix for now, investigate later"	Quick fixes mask bugs. Find root cause.
"Just try changing X and see"	One hypothesis at a time. Scientific method, not trial and error.
"Already tried 2+ fixes, one more"	3+ failed fixes = STOP. Question the architecture, not the fix.
"The error message is misleading"	Read it again carefully. Error messages are usually right.
"It works on my machine"	Reproduce in the failing environment. Your environment hides bugs.
"This can't be the cause"	Verify with evidence, not intuition. Unlikely causes are still causes.
"It's OOM, must be a large object"	Check row COUNT before row SIZE. Unbounded query > large single row.
"Round 2 fresh agent unnecessary"	Main agent rationalizes its own findings. Zero-memory agent catches dismissals.
"Graph.db not needed for this bug"	Cross-service bugs are invisible to grep. Run trace first.

---

Workflow Recommendation

MUST ATTENTION — NO EXCEPTIONS: Not in workflow? Use a direct user question:

1. Activate bugfix workflow (Recommended) — scout → investigate → debug → plan → fix → prove-fix → review → test
2. Execute $debug-investigate directly — standalone

---

Next Steps (Standalone only — skip if inside workflow)

MUST ATTENTION use a direct user question after completing. NEVER auto-decide next step:

• "Proceed with full workflow (Recommended)" — detect best workflow to continue from here
• "$fix" — apply fix based on debug findings
• "$plan-hard" — if fix requires planning first
• "Skip, continue manually" — user decides

Standalone Review Gate: Outside workflow? MUST create $review-changes task as LAST task.

---

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files.

• docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models) (read directly when relevant; do not rely on hook-injected conversation text)

Root Cause Debugging — Systematic approach, never guess-and-check.

1. Reproduce — Confirm the issue exists with evidence (error message, stack trace, screenshot)
2. Isolate — Narrow to specific file/function/line using binary search + graph trace
3. Trace — Follow data flow from input to failure point. Read actual code, don't infer.
4. Hypothesize — Form theory with confidence %. State what evidence supports/contradicts it
5. Verify — Test hypothesis with targeted grep/read. One variable at a time.
6. Fix — Address root cause, not symptoms. Verify fix doesn't break callers via graph connections

NEVER: Guess without evidence. Fix symptoms instead of cause. Skip reproduction step.

Incremental Result Persistence — MANDATORY for all sub-agents or heavy inline steps processing >3 files.

1. Before starting: Create report file plans/reports/{skill}-{date}-{slug}.md
2. After each file/section reviewed: Append findings to report immediately — never hold in memory
3. Return to main agent: Summary only (per SYNC:subagent-return-contract) with Full report: path
4. Main agent: Reads report file only when resolving specific blockers

Why: Context cutoff mid-execution loses ALL in-memory findings. Each disk write survives compaction. Partial results are better than no results.

Report naming: plans/reports/{skill-name}-{YYMMDD}-{HHmm}-{slug}.md

Sub-Agent Return Contract — When this skill spawns a sub-agent, the sub-agent MUST return ONLY this structure. Main agent reads only this summary — NEVER requests full sub-agent output inline.

## Sub-Agent Result: [skill-name]

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%

### Findings (Critical/High only — max 10 bullets)

- [severity] [file:line] [finding]

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description]

Full report: plans/reports/[skill-name]-[date]-[slug].md

Main agent reads Full report file ONLY when: (a) resolving a specific blocker, or (b) building a fix plan. Sub-agent writes full report incrementally (per SYNC:incremental-persistence) — not held in memory.

AI Mistake Prevention — Failure modes to avoid on every task:

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

1. Call the current task list first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.
2. Create one task per declared phase before phase work. When nested, prefix subjects [N.M] $skill-name — phase.
3. When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).
4. Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.
5. Mark exactly one child in_progress before work and completed immediately after evidence is written.
6. Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.

Project Reference Docs Gate — Run after task-tracking bootstrap and before target/source file reads, grep, edits, or analysis. Project docs override generic framework assumptions.

1. Identify scope: file types, domain area, and operation.
2. Required docs by trigger: always docs/project-reference/lessons.md; doc lookup docs-index-reference.md; review code-review-rules.md; backend/CQRS/API backend-patterns-reference.md; domain/entity domain-entities-reference.md; frontend/UI frontend-patterns-reference.md; styles/design scss-styling-guide.md + design-system/README.md; integration tests integration-test-reference.md; E2E e2e-test-reference.md; feature docs/specs feature-docs-reference.md; architecture/new area project-structure-reference.md.
3. Read every required doc that exists; skip absent docs as not applicable. Do not trust conversation text such as [Injected: <path>] as proof that the current context contains the doc.
4. Before target work, state: Reference docs read: ... | Missing/not applicable: ....

Blocked until: scope evaluated, required docs checked/read, lessons.md confirmed, citation emitted.

Task Tracking & External Report Persistence — Bootstrap this before execution; then run project-reference doc prefetch before target/source work.

1. Create a small task breakdown before target file reads, grep, edits, or analysis. On context loss, inspect the current task list first.
2. Mark one task in_progress before work and completed immediately after evidence; never batch transitions.
3. For plan/review work, create plans/reports/{skill}-{YYMMDD}-{HHmm}-{slug}.md before first finding.
4. Append findings after each file/section/decision and synthesize from the report file at the end.
5. Final output cites Full report: plans/reports/{filename}.

Blocked until: task breakdown exists, report path declared for plan/review work, first finding persisted before the next finding.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

Sequential Thinking Protocol — Structured multi-step reasoning for complex/ambiguous work. Use when planning, reviewing, debugging, or refining ideas where one-shot reasoning is unsafe.

Trigger when: complex problem decomposition · adaptive plans needing revision · analysis with course correction · unclear/emerging scope · multi-step solutions · hypothesis-driven debugging · cross-cutting trade-off evaluation.

Format (explicit mode — visible thought trail):

1. Thought N/M: [aspect] — one aspect per thought, state assumptions/uncertainty
2. Thought N/M [REVISION of Thought K]: ... — when prior reasoning invalidated; state Original / Why revised / Impact
3. Thought N/M [BRANCH A from Thought K]: ... — explore alternative; converge with decision rationale
4. Thought N/M [HYPOTHESIS]: ... then [VERIFICATION]: ... — test before acting
5. Thought N/N [FINAL] — only when verified, all critical aspects addressed, confidence >80%

Mandatory closers: Confidence % stated · Assumptions listed · Open questions surfaced · Next action concrete.

Stop conditions: confidence <80% on any critical decision → escalate via ask the user directly · ≥3 revisions on same thought → re-frame the problem · branch count >3 → split into sub-task.

Implicit mode: apply methodology internally without visible markers when adding markers would clutter the response (routine work where reasoning aids accuracy).

Deep-dive: see $sequential-thinking skill (.claude/skills/sequential-thinking/SKILL.md) for worked examples (api-design, debug, architecture), advanced techniques (spiral refinement, hypothesis testing, convergence), and meta-strategies (uncertainty handling, revision cascades).

Understand Code First — HARD-GATE: Do NOT write, plan, or fix until you READ existing code.

1. Search 3+ similar patterns (grep/glob) — cite file:line evidence
2. Read existing files in target area — understand structure, base classes, conventions
3. Run python .claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists
4. Map dependencies via connections or callers_of — know what depends on your target
5. Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files)
6. Re-read analysis file before implementing — never work from memory alone
7. NEVER invent new patterns when existing ones work — match exactly or document deviation

BLOCKED until: - [ ] Read target files - [ ] Grep 3+ patterns - [ ] Graph trace (if graph.db exists) - [ ] Assumptions verified with evidence

Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof.

1. Cite file:line, grep results, or framework docs for EVERY claim
2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
3. Cross-service validation required for architectural changes
4. "I don't have enough evidence" is valid and expected output

BLOCKED until: - [ ] Evidence file path (file:line) - [ ] Grep search performed - [ ] 3+ similar patterns found - [ ] Confidence level stated

Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because" If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."

Cross-Service Check — Microservices/event-driven: MANDATORY before concluding investigation, plan, spec, or feature doc. Missing downstream consumer = silent regression.

Boundary	Grep terms
Event producers	Publish, Dispatch, Send, emit, EventBus, outbox, IntegrationEvent
Event consumers	Consumer, EventHandler, Subscribe, @EventListener, inbox
Sagas/orchestration	Saga, ProcessManager, Choreography, Workflow, Orchestrator
Sync service calls	HTTP/gRPC calls to/from other services
Shared contracts	OpenAPI spec, proto, shared DTO — flag breaking changes
Data ownership	Other service reads/writes same table/collection → Shared-DB anti-pattern

Per touchpoint: owner service · message name · consumers · risk (NONE / ADDITIVE / BREAKING).

BLOCKED until: Producers scanned · Consumers scanned · Sagas checked · Contracts reviewed · Breaking-change risk flagged

Estimation Framework — Bottom-up first; SP DERIVED; output min-max range when likely ≥3d. Stack-agnostic. Baseline: 3-5yr dev, 6 productive hrs/day. AI estimate assumes Claude Code + project context.

Method:

1. Blast Radius pass (below) — drives code AND test cost
2. Decompose phases → hours/phase → bottom_up_hours = Σ phase_hours
3. likely_days = ceil(bottom_up_hours / 6) × productivity_factor
4. Sum Risk Margin (base + add-ons) → max_days = likely_days × (1 + margin)
5. min_days = likely_days × 0.9
6. Output as range when likely_days ≥3; single point allowed <3 (still record margin)
7. man_days_ai = same range × AI speedup
8. story_points DERIVED from likely_days via SP-Days — NEVER driver. Disagreement >50% → trust bottom-up

Productivity factor: 0.8 strong scaffolding+codegen+AI hooks · 1.0 mature default · 1.2 weak patterns · 1.5 greenfield

Cost Driver Heuristic (apply BEFORE work-type row):

• UI dominates in CRUD/business apps — 1.5-3x backend (states, validation, responsive, a11y, polish)
• Backend dominates ONLY: multi-aggregate invariants, cross-service contracts, schema migrations, heavy query/perf, new event flows

Reuse-vs-Create axis (PRIMARY lever, per layer):

UI tier	Cost
Reuse component on existing screen	0.1-0.3d
Add control/column to existing screen	0.3-0.8d
Compose components into NEW screen	1-2d
NEW screen, custom layout/states/validation	2-4d
NEW shared/common component (themed, tested)	3-6d+

Backend tier	Cost
Reuse query/handler from new place	0.1-0.3d
Small update existing handler/entity	0.3-0.8d
NEW query on existing repo/model	0.5-1d
NEW command/handler on existing aggregate (additive)	1-2d
NEW aggregate/entity (repo, validation, events)	2-4d
NEW cross-service contract OR schema migration	2-4d each
Multi-aggregate invariant / heavy domain rule	3-5d

Rule: Sum tiers across UI+backend+tests, apply productivity factor. Reuse short-circuits tiers — call out.

Test-Scope drivers (compute test_count EXPLICITLY — "+tests" hand-wave is #1 failure):

Driver	Count
Happy-path journeys	1 per story / AC main flow
State-machine transitions	reachable transitions × allowed actors
Multi-entity state combos	state(A) × state(B) — REACHABLE only, not Cartesian
Authorization matrix	(owner, non-owner, elevated, unauth) × each mutation
Validation rules	1 per required field / boundary / format / cross-field
UI states (per new screen/dialog)	happy, loading, empty, error, partial — present only
Negative paths / invariants	1 per violatable business rule

Test tier (Trad, incl. setup+assert+flake)	Cost
1-5 cases, fixtures reused	0.3-0.5d
6-12 cases, 1 new fixture	0.5-1d
13-25 cases, multi-entity setup	1-2d
26-50 cases OR new state-machine coverage	2-3d
>50 cases OR full E2E journey	3-5d

Test multipliers: new fixture/seed harness +0.5d · cross-service/bus assertion +0.3d each · UI E2E ×1.5 · each new role +1-2 cases

Blast Radius (mandatory pre-pass — affects code AND test):

1. Files/components directly modified — count
2. Of those, "complex" (>500 LOC, multi-handler, central, frequently-modified) — count
3. Downstream consumers (callers, event subscribers, cross-service) — list
4. Shared/common code touched (multi-app blast) — yes/no
5. Regression scope — areas needing re-test

Rule: Complex touch → add risk_factors. Each downstream consumer → +1-3 regression cases. Blast >5 areas OR >2 complex → re-evaluate SPLIT before estimating.

Risk Margin (drives max bound):

likely_days	Base margin
<1d trivial	+10%
1-2d small additive	+20%
3-4d real feature	+35%
5-7d large	+50%
8-10d very large	+75%
>10d	+100% AND flag SHOULD SPLIT

Risk-factor add-ons (additive — enumerate in risk_factors):

Factor	+margin
touches-complex-existing-feature (>500 LOC, multi-handler, central)	+20%
cross-service-contract change	+25%
schema-migration-on-populated-data	+25%
new-tech-or-unfamiliar-pattern	+30%
regression-fan-out (≥3 downstream areas re-test)	+20%
performance-or-latency-critical	+20%
concurrency-race-event-ordering	+25%
shared-common-code (multi-consumer/multi-app)	+25%
unclear-requirements-or-design	+30%

Collapse rule: total margin >100% → STOP, split (padding past 2x is dishonesty). Margin <15% on likely_days ≥5 → under-estimated, widen.

Work-Type Caps (hard ceilings on likely_days):

Work type	Max SP	Max likely
Single field / config flag / style fix	1	0.5d
Add property to existing model + bind to existing UI	2	1d
Additive endpoint + minor UI control (button/menu/column), reuses fixtures	3	2-3d
Additive endpoint + NEW UI surface OR additive multi-layer + new domain rule + 2+ test files	5	3-5d
NEW model/aggregate OR migration OR cross-module contract OR heavy test (>1.5d) OR NEW UI + non-trivial backend	8	5-7d
NEW UI surface + (NEW aggregate OR migration OR cross-service contract)	13	SHOULD split
Cross-service contract + migration combined	13	SHOULD split
Beyond	21	MUST split

SP→Days (validation only): 1=0.5d/0.25d · 2=1d/0.35d · 3=2d/0.65d · 5=4d/1.0d · 8=6d/1.5d · 13=10d/2.0d (Trad/AI likely) AI speedup: SP 1≈2x · 2-3≈3x · 5-8≈4x · 13+≈5x. AI cost = (code_gen × 1.3) + (test_gen × 1.3) (30% review overhead).

MANDATORY frontmatter:

story_points: <n>
complexity: low | medium | high | critical
man_days_traditional: '<min>-<max>d' # range when likely ≥3d; '<N>d' when <3d
man_days_ai: '<min>-<max>d'
risk_margin_pct: <n> # base + add-ons
risk_factors: [touches-complex-existing-feature, regression-fan-out] # closed-list from add-ons; [] if none
blast_radius:
    touched_areas: <n>
    complex_touched: <n>
    downstream_consumers: [list or count]
    shared_common_code: yes | no
estimate_scope_included: [code, integration-tests, frontend, i18n, docs]
estimate_scope_excluded: [unit-tests, e2e, perf, deployment, code-review-rounds]
estimate_reasoning: |
    5-7 lines covering:
    (a) UI tier — row applied
    (b) Backend tier — row applied
    (c) Test scope — case breakdown by driver, file count, fixtures, tier row
    (d) Cost driver — dominant tier + why
    (e) Blast radius — touched, complex, regression scope
    (f) Risk factors — list driving margin; why not larger/smaller
    Example: "UI: compose Form/Table/Dialog → NEW screen (~1.5d). Backend: NEW command on existing aggregate,
    reuses validation+repo (~1d). Tests: 4 transitions × 2 actors + 3 validation + 2 UI states = 13 cases,
    1 new fixture → tier 13-25 ~1.5d. Driver: UI composition + new states. Blast: 4 areas, 1 complex.
    Risk: base 35% + touches-complex +20% = 55% → max 3.9d → range 2.5-4d."

Sanity self-check:

• likely_days ≥3d and single-point? → reject, must be range
• Margin <15% on likely_days ≥5d? → under-estimated, widen
• Margin >100%? → STOP, split instead of buffer
• Complex existing feature touched, no regression budget in (c)? → reject
• Blast >5 areas OR >2 complex, no split discussion? → reject
• Purely additive on existing model AND existing UI? → cap SP 3 unless tests >1.5d
• NEW UI surface (page/complex form/dashboard)? → SP 5+ even if backend one endpoint
• Backend cross-service / migration / multi-aggregate? → SP 8+ regardless of UI
• bottom_up_hours / 6 vs SP-Days disagreement >50%? → trust bottom-up, downgrade SP
• Without tests, SP drops ≥1 bucket? → tests dominate; state explicitly
• Reasoning called out UI vs backend vs blast vs risk factors? → if missing, add

Red Flag Stop Conditions — STOP and escalate to user via ask the user directly when:

1. Confidence drops below 60% on any critical decision
2. Changes would affect >20 files (blast radius too large)
3. Cross-service boundary is being crossed
4. Security-sensitive code (auth, crypto, PII handling)
5. Breaking change detected (interface, API contract, DB schema)
6. Test coverage would decrease after changes
7. Approach requires technology/pattern not in the project

NEVER proceed past a red flag without explicit user approval.

Fix-Layer Accountability — NEVER fix at the crash site. Trace the full flow, fix at the owning layer.

AI default behavior: see error at Place A → fix Place A. This is WRONG. The crash site is a SYMPTOM, not the cause.

MANDATORY before ANY fix:

1. Trace full data flow — Map the complete path from data origin to crash site across ALL layers (storage → backend → API → frontend → UI). Identify where the bad state ENTERS, not where it CRASHES.
2. Identify the invariant owner — Which layer's contract guarantees this value is valid? That layer is responsible. Fix at the LOWEST layer that owns the invariant — not the highest layer that consumes it.
3. One fix, maximum protection — Ask: "If I fix here, does it protect ALL downstream consumers with ONE change?" If fix requires touching 3+ files with defensive checks, you are at the wrong layer — go lower.
4. Verify no bypass paths — Confirm all data flows through the fix point. Check for: direct construction skipping factories, clone/spread without re-validation, raw data not wrapped in domain models, mutations outside the model layer.

BLOCKED until: - [ ] Full data flow traced (origin → crash) - [ ] Invariant owner identified with file:line evidence - [ ] All access sites audited (grep count) - [ ] Fix layer justified (lowest layer that protects most consumers)

Anti-patterns (REJECT these):

• "Fix it where it crashes" — Crash site ≠ cause site. Trace upstream.
• "Add defensive checks at every consumer" — Scattered defense = wrong layer. One authoritative fix > many scattered guards.
• "Both fix is safer" — Pick ONE authoritative layer. Redundant checks across layers send mixed signals about who owns the invariant.

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

MUST ATTENTION apply sequential-thinking — multi-step Thought N/M, REVISION/BRANCH/HYPOTHESIS markers, confidence % closer; see $sequential-thinking skill.

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

• MANDATORY Bootstrap task tracking before target work; transition one task at a time.
• MANDATORY Persist plan/review findings to plans/reports/ incrementally and synthesize from disk.

• MANDATORY After task-tracking bootstrap and before target/source work, read required project-reference docs and cite Reference docs read: ....
• MANDATORY Always include lessons.md; project conventions override generic defaults.

• MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
• MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] $skill-name — phase prefixes and one-in_progress discipline.

Prompt-Enhance Closing Anchors

IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

Closing Reminders

MUST ATTENTION Phase 0 FIRST — classify bug type, route to specialized agent (performance-optimizer / security-auditor) before any investigation MUST ATTENTION NEVER fix at crash site — trace full data flow, fix at invariant-owning layer MUST ATTENTION NEVER report root cause without file:line evidence; Confidence <60% = DO NOT recommend MUST ATTENTION NEVER declare confirmed root cause after Round 1 alone — Fresh Eyes Protocol required MUST ATTENTION run graph trace when graph.db exists — reveals bus consumers and event handlers grep cannot see MUST ATTENTION OOM → check row COUNT before row SIZE; 3+ failed fixes → STOP, escalate to user MUST ATTENTION task tracking before starting; $prove-fix MUST run after $fix applies changes

Anti-Rationalization:

Evasion	Rebuttal
"Too simple for Phase 0"	Root cause assumptions waste more time than classification. Apply anyway.
"Already traced, no graph needed"	Show file:line evidence. No proof = no trace.
"Round 2 fresh agent wastes time"	Main agent rationalizes its own mistakes. Zero-memory agent is non-negotiable.
"This is a frontend bug, no graph"	Frontend → backend → bus chains exist. Run trace first.

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

1. DETECT: Match prompt against workflow catalog
2. ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better
3. ASK (REQUIRED FORMAT): Use a direct user question with this structure:
   • Question: "Which workflow do you want to activate?"
   • Option 1: "Activate [BestMatch Workflow] (Recommended)"
   • Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)
4. ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually
5. CREATE TASKS: task tracking for ALL workflow steps
6. EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows.

Learned Lessons

Lessons Learned

[CRITICAL] Hard-won project debugging/architecture rules. MUST ATTENTION apply BEFORE forming hypothesis or writing code.

Quick Summary

Goal: Prevent recurrence of known failure patterns — debugging, architecture, naming, AI orchestration, environment.

Top Rules (apply always):

• MUST ATTENTION verify ALL preconditions (config, env, DB names, DI regs) BEFORE code-layer hypothesis
• MUST ATTENTION fix responsible layer — NEVER patch symptom sites with caller-specific defensive code
• MUST ATTENTION use ExecuteInjectScopedAsync for parallel async + repo/UoW — NEVER ExecuteUowTask
• MUST ATTENTION name by PURPOSE not CONTENT — adding member forces rename = abstraction broken
• MUST ATTENTION persist sub-agent findings incrementally after each file — NEVER batch at end
• MUST ATTENTION Windows bash: verify Python alias (where python/where py) — NEVER assume python/python3 resolves

---

Debugging & Root Cause Reasoning

• [2026-04-11] Holistic-first: verify environment before code. Failure → list ALL preconditions (config, env vars, DB names, endpoints, DI regs, credentials, permissions, data prerequisites) → verify each via evidence (grep/cat/query) BEFORE code-layer hypothesis. Worst rabbit holes: diving nearest layer while bug sits elsewhere — e.g., hours debugging "sync timeout", real cause: test appsettings pointing wrong DB. Cheapest check first.
• [2026-04-01] Ask "whose responsibility?" before fixing. Trace: bug in caller (wrong data) or callee (wrong handling)? Fix responsible layer — NEVER patch symptom site masking real issue.
• [2026-04-01] Trace data lifecycle, not error site. Follow data: creation → transformation → consumption. Bug usually where data created wrong, not consumed.
• [2026-04-01] Code is caller-agnostic. Functions/handlers/consumers don't know who invokes them. Comments/guards/messages describe business intent — NEVER reference specific callers (tests, seeders, scripts).

Architecture Invariants

• [2026-03-31] ParallelAsync + repo/UoW MUST use ExecuteInjectScopedAsync, NEVER ExecuteUowTask. ExecuteUowTask creates new UoW but reuses outer DI scope (same DbContext) — parallel iterations sharing non-thread-safe DbContext silently corrupt data. ExecuteInjectScopedAsync creates new UoW + new DI scope (fresh repo per iteration).
• [2026-03-31] Bus message naming MUST include service name prefix — core services NEVER consume feature events. Prefix declares schema ownership (AccountUserEntityEventBusMessage = Accounts owns). Core services (Accounts, Communication) are leaders. Feature services (Growth, Talents) sending to core MUST use {CoreServiceName}...RequestBusMessage — never define own event for core to consume.

Naming & Abstraction

• [2026-04-12] Name PURPOSE not CONTENT — "OrXxx" anti-pattern. HrManagerOrHrOrPayrollHrOperationsPolicy names set members, not what it guards. Add role → rename = broken abstraction. Rule: names express DOES/GUARDS, not CONTAINS. Test: adding/removing member forces rename? YES = content-driven = bad → rename to purpose (e.g., HrOperationsAccessPolicy). Nuance: "Or" fine in behavioral idioms (FirstOrDefault, SuccessOrThrow) — expresses HAPPENS, not membership.

Environment & Tooling

• [2026-04-20] Windows bash: NEVER assume python/python3 resolves — verify alias first. Python may not be in bash PATH under those names. Check: where python / where py. Prefer py (Windows Python Launcher) for one-liners, node if JS alternative exists.

Test-specific lessons → docs/project-reference/integration-test-reference.md Lessons Learned section. Production-code anti-patterns → docs/project-reference/backend-patterns-reference.md Anti-Patterns section. Generic debugging/refactoring reminders → System Lessons in .claude/hooks/lib/prompt-injections.cjs.

---

Closing Reminders

• IMPORTANT MUST ATTENTION holistic-first: verify ALL preconditions (config, env, DB names, endpoints, DI regs) BEFORE code-layer hypothesis — cheapest check first
• IMPORTANT MUST ATTENTION fix responsible layer — NEVER patch symptom site; trace caller (wrong data) vs callee (wrong handling), fix root owner
• IMPORTANT MUST ATTENTION parallel async + repo/UoW → ALWAYS ExecuteInjectScopedAsync, NEVER ExecuteUowTask (shared DbContext = silent data corruption)
• IMPORTANT MUST ATTENTION bus message prefix = schema ownership; feature services NEVER define events for core services — use {CoreServiceName}...RequestBusMessage
• IMPORTANT MUST ATTENTION name by PURPOSE — adding/removing member forces rename = broken abstraction
• IMPORTANT MUST ATTENTION sub-agents MUST write findings after each file/section — NEVER batch all findings into one final write
• IMPORTANT MUST ATTENTION Windows bash: NEVER assume python/python3 resolves — run where python/where py first, use py launcher or node

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
6. Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.