custom-agent

name	custom-agent
description	[AI & Tools] Use when you need create, verify, or enhance Claude Code custom agents (Claude Code custom agent files).

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• 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 uses static project-reference loading instead of runtime-injected project docs. 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)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

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 authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
• Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
• Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
• 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.

Quick Summary

Goal: Create new custom agents, audit existing agent quality, or enhance agent definitions.

Workflow: Detect mode (Create/Audit/Enhance) from $ARGUMENTS → Execute → Validate

Key Rules:

• Agent files: .claude/agents/{name}.md with YAML frontmatter + markdown body as system prompt
• Agent does NOT inherit Claude Code system prompt — write complete instructions
• Minimize tools to only what the agent needs
• System prompt structure: ## Role → ## Workflow → ## Key Rules → ## Output

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Modes

Mode	Trigger	Action
Create	$ARGUMENTS describes a new agent	Create agent file
Audit	mentions verify, audit, review, check, quality	Audit existing agents
Enhance	mentions refactor, enhance, improve, optimize	Improve existing agent

Mode 1: Create Agent

1. Clarify — a direct user question: purpose, read-only vs read-write, model preference, memory needs
2. Check Existing — Glob .claude/agents/*.md for similar agents. Avoid duplication.
3. Scaffold — Create .claude/agents/{name}.md using frontmatter template below
4. Write System Prompt — Structure: ## Role → ## Workflow → ## Key Rules → ## Output
5. Validate — Run audit checklist below

Mode 2: Audit Agents

1. Discover — Glob .claude/agents/*.md
2. Parse — Read first 30 lines of each, extract frontmatter
3. Validate — Check each audit rule below
4. Report — Issues grouped by severity (Error > Warning > Info), include quality scores
5. Fix — If user confirms, fix Error-level issues automatically

Mode 3: Enhance Agent

1. Read — Load specified agent file
2. Analyze — Check against best practices and audit checklist
3. Recommend — List improvements with rationale
4. Apply — If user confirms, apply enhancements

---

Agent Frontmatter Schema

---
# REQUIRED
name: my-agent # Lowercase + hyphens only
description: >- # Claude uses this to decide when to delegate
    Use this agent when [specific trigger scenarios].

# OPTIONAL — Tools
tools: Read, Grep, Glob, Bash # Allowlist (omit both → inherits all)
disallowedTools: Write, Edit # Denylist (removes from inherited set)
# Task(agent1, agent2) restricts spawnable subagents

# OPTIONAL — Model
model: inherit # inherit | sonnet | opus | haiku

# OPTIONAL — Permissions
permissionMode: default # default | acceptEdits | dontAsk | bypassPermissions | plan

# OPTIONAL — Skills (content injected at startup)
skills:
    - skill-name

# OPTIONAL — MCP Servers
mcpServers:
    - server-name

# OPTIONAL — Hooks (scoped to this agent)
hooks:
    PreToolUse:
        - matcher: 'Bash'
          hooks:
                
                 


  


  
  

Tool Restriction Patterns

Agent Type	Recommended tools
Explorer/Scout	Read, Grep, Glob, Bash
Reviewer (read-only)	Read, Grep, Glob
Writer/Implementer	Read, Write, Edit, Grep, Glob, Bash
Researcher	Read, Grep, Glob, WebFetch, WebSearch
Orchestrator	Read, Grep, Glob, Task(sub1, sub2)

Available tools: Read, Write, Edit, MultiEdit, Glob, Grep, Bash, WebFetch, WebSearch, Task, NotebookRead, NotebookEdit, task tracking, TaskUpdate, ask the user directly, + MCP tools.

Model Selection

Model	Best For
haiku	Fast read-only: scanning, search, file listing
sonnet	Balanced: code review, debugging, analysis
opus	High-stakes: architecture, complex implementation. Better quality for code review, debugging, analysis
inherit	Default — match parent's model

Description Best Practices

# BAD — too vague, Claude won't auto-delegate
description: Reviews code

# GOOD — specific trigger conditions
description: >-
  Use this agent for comprehensive code review after implementing features,
  before merging PRs, or when assessing code quality and technical debt.

• Include "Use this agent when..." phrasing with concrete scenarios
• Add "use proactively" to encourage auto-invocation

Common Anti-Patterns

Anti-Pattern	Fix
No tool restrictions	Add tools allowlist
Vague description	Write specific trigger conditions
Giant system prompt	Keep concise, use skills for detail
Recursive subagents	Restrict Task in tools
Windows long prompts (>8191 chars)	Use file-based agents, not --agents CLI

Context Passing

• Agent receives ONLY its system prompt + task prompt — NOT parent conversation
• Parent receives ONLY agent's final result — NOT intermediate tool calls
• This isolation is the primary context management benefit

Audit Checklist

#	Check	Rule	Severity
1	Frontmatter exists	Must have --- delimiters	Error
2	Name present & valid	Lowercase + hyphens only	Error
3	Description present	Non-empty, >20 chars	Error
4	No duplicate names	Unique across all agent files	Error
5	Description quality	Specific trigger scenarios	Warning
6	Tools minimal	Only what agent needs	Warning
7	Prompt structure	Has ## Role + ## Workflow	Warning
8	Model set	When task differs from default	Info

Quality Score: Valid frontmatter (20) + Description >50 chars (20) + Tools restricted (15) + Role section (15) + Workflow section (10) + Model set (10) = 90. Rating: 80+ Excellent, 60-79 Good, 40-59 Needs Work, <40 Poor.

File Priority (highest first)

1. --agents CLI flag (session only)
2. .claude/agents/*.md (project)
3. ~/.claude/agents/*.md (user)
4. Plugin agents/ directory

Same name across levels: higher-priority wins. Use claude agents CLI to list all.

Requirements

$ARGUMENTS

---

IMPORTANT Task Planning Notes (MUST ATTENTION FOLLOW)

• Always break work into small todo tasks
• Always add a final review todo 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. For simple tasks, AI MUST ATTENTION ask user whether to skip.

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

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

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.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

Closing Reminders

Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

• AI Mistakes: holistic-first debug, fix at responsible layer, surgical diff, verify ALL outputs.

• Critical Thinking: traced file:line proof every claim, confidence >80% to act, NEVER guess.

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting

• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code

• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)

• MANDATORY 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 task tracking.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs

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

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. Any supported AI tool may execute when this shared context and local docs are available.

1. DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
2. ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3. AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
4. ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
5. CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
6. EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

1. Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
2. Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.
3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
6. Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync
7. If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

---

SYNC:ai-sdd-artifact-contract:reminder

• MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
• MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
• MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
• MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [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.

[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/$security-review/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [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. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

Common AI Mistake Prevention (System Lessons)

• Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
• Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
• Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
• After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
• Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
• Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
• When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
• Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
• Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
• Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
• Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
• Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
• Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
• When debugging, ask "whose responsibility?" before fixing. Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
• Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
• Assume existing values are intentional — ask WHY before changing. Pattern-matching as "wrong" skips context. Before changing any constant/limit/flag: read comments, git blame, surrounding code.