scan-all

name	scan-all
version	1.0.0
description	[Documentation] Use when you need orchestrate all reference doc scans in parallel.

Quick Summary

Goal: Run all 12 scan-* skills in parallel and clear the staleness gate.

Workflow:

1. Check Prerequisites — Verify project has content (not empty)
2. Launch Parallel Scans — All 12 skills simultaneously
3. Collect Results — Read scan output from reference docs
4. Clear Staleness Flag — Remove .claude/.scan-stale so the gate unblocks
5. Build Knowledge Graph — Run /graph-build to update structural graph
6. Enhance Docs — Run /prompt-enhance on all 12 scanned docs
7. Summarize — Report what was refreshed

Key Rules:

• All 12 scans run in PARALLEL for speed
• Does NOT modify code — only populates docs/project-reference/
• Clears .claude/.scan-stale flag after completion
• /prompt-enhance ensures AI attention anchoring on all generated docs

When to Use

• Staleness gate blocks prompts ("BLOCKED: Reference docs are stale")
• First time using easy-claude on an existing project (project onboarding)
• Periodic refresh when codebase has changed significantly
• User runs /scan-all manually

When to Skip

• Empty/greenfield project (no code to scan)
• All reference docs are already fresh (no staleness warning)

Execution

Launch all 12 scan skills in parallel:

#	Skill	Target Doc
1	/scan-project-structure	project-structure-reference.md
2	/scan-backend-patterns	backend-patterns-reference.md
3	/scan-seed-test-data	seed-test-data-reference.md
4	/scan-frontend-patterns	frontend-patterns-reference.md
5	/scan-integration-tests	integration-test-reference.md
6	/scan-feature-docs	feature-docs-reference.md
7	/scan-code-review-rules	code-review-rules.md
8	/scan-scss-styling	scss-styling-guide.md
9	/scan-design-system	design-system/README.md
10	/scan-e2e-tests	e2e-test-reference.md
11	/scan-domain-entities	domain-entities-reference.md
12	/scan-docs-index	docs-index-reference.md

Post-Scan Cleanup

After all scans complete, clear the staleness flag:

node -e "require('./.claude/hooks/lib/session-init-helpers.cjs').refreshScanStaleFlag()"

This re-evaluates all docs and removes the .scan-stale gate if all are now fresh.

Post-Scan: Build Knowledge Graph (MANDATORY)

After all scans complete, MUST ATTENTION create a follow-up task:

TaskCreate: "Run /graph-build to build/update code knowledge graph"

The knowledge graph uses project-config.json (populated by scans) for API connector patterns and implicit connection rules. Building the graph after scans ensures:

• Frontend↔backend API_ENDPOINT edges use accurate service paths
• MESSAGE_BUS implicit edges use correct consumer patterns
• Graph trace shows full system flow (frontend → backend → cross-service consumers)

python .claude/scripts/code_graph build --json

Post-Scan: Enhance Generated Docs (MANDATORY)

After graph build, MUST ATTENTION create tasks to run /prompt-enhance on all scanned docs. Reference docs are injected into AI context — attention anchoring (top/bottom summaries, inline READ summaries, token density) directly improves AI output quality.

TaskCreate one task per doc, parallel OK:

#	Target File
1	docs/project-reference/project-structure-reference.md
2	docs/project-reference/backend-patterns-reference.md
3	docs/project-reference/seed-test-data-reference.md
4	docs/project-reference/frontend-patterns-reference.md
5	docs/project-reference/integration-test-reference.md
6	docs/project-reference/feature-docs-reference.md
7	docs/project-reference/code-review-rules.md
8	docs/project-reference/scss-styling-guide.md
9	docs/project-reference/design-system/README.md
10	docs/project-reference/e2e-test-reference.md
11	docs/project-reference/domain-entities-reference.md
12	docs/project-reference/docs-index-reference.md

Run via: /prompt-enhance docs/project-reference/{filename}

Summary Output

After all scans complete, report:

"Scan All Complete:

• {X}/12 scans succeeded
• Reference docs refreshed in docs/project-reference/
• Staleness gate cleared
• Prompt-enhanced {Y}/12 docs
• Knowledge graph rebuilt via /graph-build"

---

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting.

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.

Output Quality — Token efficiency without sacrificing quality.

1. No inventories/counts — AI can grep | wc -l. Counts go stale instantly
2. No directory trees — AI can glob/ls. Use 1-line path conventions
3. No TOCs — AI reads linearly. TOC wastes tokens
4. No examples that repeat what rules say — one example only if non-obvious
5. Lead with answer, not reasoning. Skip filler words and preamble
6. Sacrifice grammar for concision in reports
7. Unresolved questions at end, if any

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.

IMPORTANT MUST ATTENTION follow output quality rules: no counts/trees/TOCs, rules > descriptions, 1 example per pattern, primacy-recency anchoring.

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

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

Closing Reminders

IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

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