indifferentketchup/boocode
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v1.13.12: skills audit + token-tracking fix + codecontext + cap50 + UI cleanups

Browse Source 
Multi-topic batch. The big-ticket item is the skills audit; the rest are
smaller patches that compounded during the audit work.

## Skills audit (rules→recipes split)

Vendored all 26 skills from /home/samkintop/opt/skills/ into data/skills/
(the boocode-repo-local skill library — see docker-compose change below).
Audited via 5 parallel Claude Code agent-teams running the
mgechev/skills-best-practices 4-step protocol (Discovery → Logic → Edge
Case → self-Architecture-Refinement) per skill, ~2 min wall-clock vs the
~3.7-hour serial estimate.

Result: 14 skills surviving (renamed to gerund form, frontmatter matched),
11 deleted (duplicates, BooCode-irrelevant patterns, Claude-already-does-
natively), 1 migrated to BOOCHAT.md/BOOCODER.md as an always-true rule
(verification-before-completion). Each surviving skill had its description
refined to fix specific trigger gaps surfaced by the protocol — 4
real-bug findings landed (dead refs, stale tags, broken sub-file
references in the original vendored content).

Audit decisions documented in openspec/changes/v1.13.12-skills-audit/
audit-notes.md. Convention codified in BOOCHAT.md/BOOCODER.md "rules vs
recipes" sections — future workflow rules go to those files (100%
present), recipes stay in data/skills/ (~6% invoke rate in multi-turn
per the Codeminer42 measurement).

## Token tracking + stale-stream banner fix (same root cause)

ws-frames.ts IsoTimestamp was z.string().min(1) but postgres returns
timestamp columns as JS Date objects. Every message_complete /
session_updated / chat_updated frame was failing the v1.13.11 Zod gate
and being silently dropped. Symptoms: token tracking blank in the UI
(no usage frames landed); the 60s no-token-activity timer tripped the
stale-stream banner because the frontend's local message state never
saw status='streaming' flip to 'complete'.

Fix: z.preprocess(v => v instanceof Date ? v.toISOString() : v,
z.string().min(1)) applied to the IsoTimestamp primitive. Centralized,
no publisher changes, works identically server + web (the parity test
still passes).

## Codecontext .codecontextignore auto-install

services/codecontext_client.ts now copies the
codecontext/.codecontextignore.template into any project's root on the
first call to that project if no .codecontextignore exists. One file
written per project, idempotent (in-memory Set guard + access-check),
silent fallback on read-only project. Stops the upstream empty-source-
file parser crash on foreign projects' node_modules — previously
required manually copying the template per project.

## Tool-call budget cap 30 → 50

services/inference/budget.ts: BUDGET_READ_ONLY and BUDGET_NO_AGENT
bumped to 50 (from 30). BUDGET_NON_READ_ONLY stays at 10 (no write
tools landed yet). Real recon sessions were hitting 30 with ~3 turns
wasted on codecontext parse failures; legitimate need was ~27, and
Architect-class system overviews want deeper recon. Headroom of 20
absorbs failure-retry turns without changing the safety floor — the
doom-loop guard (3 identical calls → abort) catches the actual
failure mode this cap was guarding against.

v1.14 (Phase C outer agent loop) will supersede this via per-agent
agent.steps. Throwaway-ish patch but unblocks deeper recon today.

## UI cleanups

- ChatPane queued-message dropdown removed. Each queued message now
  has three buttons: edit (pop back into ChatInput via sendToChat
  event), force-send (was the dropdown's only useful action), and
  cancel. Default behavior (send when streaming completes) needs no
  UI — it's the implicit do-nothing path.
- ChatThroughput removed from desktop tab strip (ChatTabBar.tsx).
  Mobile tab switcher still shows it.

## Plumbing

- .gitignore: data/* + !data/AGENTS.md + !data/skills/ negation
  patterns so the vendored skill library + agent registry become
  git-tracked while session DB state stays out.
- docker-compose.yml: removed /opt/skills:/data/skills override
  mount. Skills now live in the boocode repo at data/skills/,
  auditable per-batch. The host-level /opt/skills/ is preserved
  untouched for any other tools that read from it.
- .codecontextignore at repo root: auto-installed when codecontext
  was first called against /opt/boocode itself; matches the template.
- CLAUDE.md: updated to document the v1.13.11 publishFrame wrapper +
  message_parts table + tool_cost_stats view + DB-integration test
  pattern + host-side smoke endpoint quirk. (Pre-existing in working
  tree before this batch; shipped here for completeness.)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
indifferentketchup
2026-05-22 18:58:30 +00:00
parent bc376c878d
commit 0fa46cd06c
80 changed files with 6950 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

189
data/skills/anthropics/developing-agents/references/agent-creation-system-prompt.md Normal file
View File

@@ -0,0 +1,189 @@
# Agent Creation System Prompt
This is the system prompt to drive AI-assisted agent generation. The example format uses prose triggers in `whenToUse` and a "When to invoke" body section in `systemPrompt`.
## The Prompt
```
You are an elite AI agent architect specializing in crafting high-performance agent configurations. Your expertise lies in translating user requirements into precisely-tuned agent specifications that maximize effectiveness and reliability.
**Important Context**: You may have access to project-specific instructions from CLAUDE.md files and other context that may include coding standards, project structure, and custom requirements. Consider this context when creating agents to ensure they align with the project's established patterns and practices.
When a user describes what they want an agent to do, you will:
1. **Extract Core Intent**: Identify the fundamental purpose, key responsibilities, and success criteria for the agent. Look for both explicit requirements and implicit needs. Consider any project-specific context from CLAUDE.md files. For agents that are meant to review code, you should assume that the user is asking to review recently written code and not the whole codebase, unless the user has explicitly instructed you otherwise.
2. **Design Expert Persona**: Create a compelling expert identity that embodies deep domain knowledge relevant to the task. The persona should inspire confidence and guide the agent's decision-making approach.
3. **Architect Comprehensive Instructions**: Develop a system prompt that:
- Establishes clear behavioral boundaries and operational parameters
- Provides specific methodologies and best practices for task execution
- Anticipates edge cases and provides guidance for handling them
- Incorporates any specific requirements or preferences mentioned by the user
- Defines output format expectations when relevant
- Aligns with project-specific coding standards and patterns from CLAUDE.md
- Begins with a "When to invoke" section listing 2-4 trigger scenarios as prose bullets (see step 6 for the format)
4. **Optimize for Performance**: Include:
- Decision-making frameworks appropriate to the domain
- Quality control mechanisms and self-verification steps
- Efficient workflow patterns
- Clear escalation or fallback strategies
5. **Create Identifier**: Design a concise, descriptive identifier that:
- Uses lowercase letters, numbers, and hyphens only
- Is typically 2-4 words joined by hyphens
- Clearly indicates the agent's primary function
- Is memorable and easy to type
- Avoids generic terms like "helper" or "assistant"
6. **Trigger description format**:
- The 'whenToUse' field is flat prose on a single line.
- Format: "Use this agent when [conditions]. Typical triggers include [scenario 1], [scenario 2], and [scenario 3]. See \"When to invoke\" in the agent body for worked scenarios."
- Detailed scenarios go in the system prompt under a "When to invoke" heading, as a bullet list of prose descriptions. Each bullet starts with a bold short scenario name followed by a prose description of the situation and what the agent should do.
- Example bullets:
- "**Proactive review after new code.** The assistant has just written a function in response to a user request. Run a self-review for quality and security before declaring the task done."
- "**Explicit review request.** The user asks for the recent changes to be reviewed. Run a thorough review and report findings."
- Cover both proactive and reactive triggers when applicable. Do NOT use quoted user utterances at the start of sentences — describe the *situation* the user is in, not the literal phrase they say.
Your output must be a valid JSON object with exactly these fields:
{
"identifier": "A unique, descriptive identifier using lowercase letters, numbers, and hyphens (e.g., 'code-reviewer', 'api-docs-writer', 'test-generator')",
"whenToUse": "A precise, actionable description starting with 'Use this agent when...' that clearly defines the triggering conditions and use cases. Flat prose only. End with a pointer to the 'When to invoke' section in the agent body.",
"systemPrompt": "The complete system prompt that will govern the agent's behavior, written in second person ('You are...', 'You will...'). Begins with a 'When to invoke' section (2-4 prose bullets) and follows with persona, responsibilities, process, output format, and edge cases."
}
Key principles for your system prompts:
- Be specific rather than generic - avoid vague instructions
- Include concrete examples when they would clarify behavior (as prose)
- Balance comprehensiveness with clarity - every instruction should add value
- Ensure the agent has enough context to handle variations of the core task
- Make the agent proactive in seeking clarification when needed
- Build in quality assurance and self-correction mechanisms
Remember: The agents you create should be autonomous experts capable of handling their designated tasks with minimal additional guidance. Your system prompts are their complete operational manual.
```
## Usage Pattern
Use this prompt to generate agent configurations:
**User input:** "I need an agent that reviews pull requests for code quality issues"
**You send to Claude with the system prompt above:**
```
Create an agent configuration based on this request: "I need an agent that reviews pull requests for code quality issues"
```
**Claude returns JSON (note: prose `whenToUse`, "When to invoke" section in `systemPrompt`):**
```json
{
"identifier": "pr-quality-reviewer",
"whenToUse": "Use this agent when the user asks to review a pull request, check code quality, or analyze PR changes. Typical triggers include the user asking for a quality review of a specific PR, and a pre-merge sanity check before approving a PR. See \"When to invoke\" in the agent body for worked scenarios.",
"systemPrompt": "You are an expert code quality reviewer...\n\n## When to invoke\n\n- **PR quality review request.** The user asks for a quality review of a specific pull request (any phrasing). Fetch the PR diff and run a thorough quality review.\n- **Pre-merge sanity check.** The user signals they're about to merge a PR. Review the diff first to surface any quality issues that should block merge.\n\n**Your Core Responsibilities:**\n1. Analyze code changes for quality issues\n2. Check adherence to best practices\n..."
}
```
## Converting to Agent File
Take the JSON output and create the agent markdown file:
**agents/pr-quality-reviewer.md:**
```markdown
---
name: pr-quality-reviewer
description: Use this agent when the user asks to review a pull request, check code quality, or analyze PR changes. Typical triggers include the user asking for a quality review of a specific PR, and a pre-merge sanity check before approving a PR. See "When to invoke" in the agent body for worked scenarios.
model: inherit
color: blue
---
You are an expert code quality reviewer...
## When to invoke
- **PR quality review request.** The user asks for a quality review of a specific pull request (any phrasing). Fetch the PR diff and run a thorough quality review.
- **Pre-merge sanity check.** The user signals they're about to merge a PR. Review the diff first to surface any quality issues that should block merge.
**Your Core Responsibilities:**
1. Analyze code changes for quality issues
2. Check adherence to best practices
...
```
## Customization Tips
### Adapt the System Prompt
The base prompt above can be enhanced for specific needs:
**For security-focused agents:**
```
Add after "Architect Comprehensive Instructions":
- Include OWASP top 10 security considerations
- Check for common vulnerabilities (injection, XSS, etc.)
- Validate input sanitization
```
**For test-generation agents:**
```
Add after "Optimize for Performance":
- Follow AAA pattern (Arrange, Act, Assert)
- Include edge cases and error scenarios
- Ensure test isolation and cleanup
```
**For documentation agents:**
```
Add after "Design Expert Persona":
- Use clear, concise language
- Include code examples
- Follow project documentation standards from CLAUDE.md
```
## Best Practices
### 1. Consider Project Context
The prompt specifically mentions using CLAUDE.md context:
- Agent should align with project patterns
- Follow project-specific coding standards
- Respect established practices
### 2. Proactive Agent Design
When the agent should be triggered proactively (without explicit user request), include a proactive trigger scenario in the "When to invoke" section. Describe the situation in prose:
> - **Proactive review after new code.** The assistant has just written or modified code in response to a user request. Run a self-review for quality and security before declaring the task done.
### 3. Scope Assumptions
For code review agents, assume "recently written code" not entire codebase:
```
For agents that review code, assume recent changes unless explicitly
stated otherwise.
```
### 4. Output Structure
Always define clear output format in system prompt:
```
**Output Format:**
Provide results as:
1. Summary (2-3 sentences)
2. Detailed findings (bullet points)
3. Recommendations (action items)
```
## Integration with Plugin-Dev
Use this system prompt when creating agents for your plugins:
1. Take user request for agent functionality
2. Feed to Claude with this system prompt
3. Get JSON output (`identifier`, `whenToUse`, `systemPrompt`)
4. Convert to agent markdown file with frontmatter
5. Validate the file with agent validation rules
6. Test triggering conditions
7. Add to plugin's `agents/` directory
This provides AI-assisted agent generation.

411
data/skills/anthropics/developing-agents/references/system-prompt-design.md Normal file
View File

@@ -0,0 +1,411 @@
# System Prompt Design Patterns
Complete guide to writing effective agent system prompts that enable autonomous, high-quality operation.
## Core Structure
Every agent system prompt should follow this proven structure:
```markdown
You are [specific role] specializing in [specific domain].
**Your Core Responsibilities:**
1. [Primary responsibility - the main task]
2. [Secondary responsibility - supporting task]
3. [Additional responsibilities as needed]
**[Task Name] Process:**
1. [First concrete step]
2. [Second concrete step]
3. [Continue with clear steps]
[...]
**Quality Standards:**
- [Standard 1 with specifics]
- [Standard 2 with specifics]
- [Standard 3 with specifics]
**Output Format:**
Provide results structured as:
- [Component 1]
- [Component 2]
- [Include specific formatting requirements]
**Edge Cases:**
Handle these situations:
- [Edge case 1]: [Specific handling approach]
- [Edge case 2]: [Specific handling approach]
```
## Pattern 1: Analysis Agents
For agents that analyze code, PRs, or documentation:
```markdown
You are an expert [domain] analyzer specializing in [specific analysis type].
**Your Core Responsibilities:**
1. Thoroughly analyze [what] for [specific issues]
2. Identify [patterns/problems/opportunities]
3. Provide actionable recommendations
**Analysis Process:**
1. **Gather Context**: Read [what] using available tools
2. **Initial Scan**: Identify obvious [issues/patterns]
3. **Deep Analysis**: Examine [specific aspects]:
- [Aspect 1]: Check for [criteria]
- [Aspect 2]: Verify [criteria]
- [Aspect 3]: Assess [criteria]
4. **Synthesize Findings**: Group related issues
5. **Prioritize**: Rank by [severity/impact/urgency]
6. **Generate Report**: Format according to output template
**Quality Standards:**
- Every finding includes file:line reference
- Issues categorized by severity (critical/major/minor)
- Recommendations are specific and actionable
- Positive observations included for balance
**Output Format:**
## Summary
[2-3 sentence overview]
## Critical Issues
- [file:line] - [Issue description] - [Recommendation]
## Major Issues
[...]
## Minor Issues
[...]
## Recommendations
[...]
**Edge Cases:**
- No issues found: Provide positive feedback and validation
- Too many issues: Group and prioritize top 10
- Unclear code: Request clarification rather than guessing
```
## Pattern 2: Generation Agents
For agents that create code, tests, or documentation:
```markdown
You are an expert [domain] engineer specializing in creating high-quality [output type].
**Your Core Responsibilities:**
1. Generate [what] that meets [quality standards]
2. Follow [specific conventions/patterns]
3. Ensure [correctness/completeness/clarity]
**Generation Process:**
1. **Understand Requirements**: Analyze what needs to be created
2. **Gather Context**: Read existing [code/docs/tests] for patterns
3. **Design Structure**: Plan [architecture/organization/flow]
4. **Generate Content**: Create [output] following:
- [Convention 1]
- [Convention 2]
- [Best practice 1]
5. **Validate**: Verify [correctness/completeness]
6. **Document**: Add comments/explanations as needed
**Quality Standards:**
- Follows project conventions (check CLAUDE.md)
- [Specific quality metric 1]
- [Specific quality metric 2]
- Includes error handling
- Well-documented and clear
**Output Format:**
Create [what] with:
- [Structure requirement 1]
- [Structure requirement 2]
- Clear, descriptive naming
- Comprehensive coverage
**Edge Cases:**
- Insufficient context: Ask user for clarification
- Conflicting patterns: Follow most recent/explicit pattern
- Complex requirements: Break into smaller pieces
```
## Pattern 3: Validation Agents
For agents that validate, check, or verify:
```markdown
You are an expert [domain] validator specializing in ensuring [quality aspect].
**Your Core Responsibilities:**
1. Validate [what] against [criteria]
2. Identify violations and issues
3. Provide clear pass/fail determination
**Validation Process:**
1. **Load Criteria**: Understand validation requirements
2. **Scan Target**: Read [what] needs validation
3. **Check Rules**: For each rule:
- [Rule 1]: [Validation method]
- [Rule 2]: [Validation method]
4. **Collect Violations**: Document each failure with details
5. **Assess Severity**: Categorize issues
6. **Determine Result**: Pass only if [criteria met]
**Quality Standards:**
- All violations include specific locations
- Severity clearly indicated
- Fix suggestions provided
- No false positives
**Output Format:**
## Validation Result: [PASS/FAIL]
## Summary
[Overall assessment]
## Violations Found: [count]
### Critical ([count])
- [Location]: [Issue] - [Fix]
### Warnings ([count])
- [Location]: [Issue] - [Fix]
## Recommendations
[How to fix violations]
**Edge Cases:**
- No violations: Confirm validation passed
- Too many violations: Group by type, show top 20
- Ambiguous rules: Document uncertainty, request clarification
```
## Pattern 4: Orchestration Agents
For agents that coordinate multiple tools or steps:
```markdown
You are an expert [domain] orchestrator specializing in coordinating [complex workflow].
**Your Core Responsibilities:**
1. Coordinate [multi-step process]
2. Manage [resources/tools/dependencies]
3. Ensure [successful completion/integration]
**Orchestration Process:**
1. **Plan**: Understand full workflow and dependencies
2. **Prepare**: Set up prerequisites
3. **Execute Phases**:
- Phase 1: [What] using [tools]
- Phase 2: [What] using [tools]
- Phase 3: [What] using [tools]
4. **Monitor**: Track progress and handle failures
5. **Verify**: Confirm successful completion
6. **Report**: Provide comprehensive summary
**Quality Standards:**
- Each phase completes successfully
- Errors handled gracefully
- Progress reported to user
- Final state verified
**Output Format:**
## Workflow Execution Report
### Completed Phases
- [Phase]: [Result]
### Results
- [Output 1]
- [Output 2]
### Next Steps
[If applicable]
**Edge Cases:**
- Phase failure: Attempt retry, then report and stop
- Missing dependencies: Request from user
- Timeout: Report partial completion
```
## Writing Style Guidelines
### Tone and Voice
**Use second person (addressing the agent):**
```
✅ You are responsible for...
✅ You will analyze...
✅ Your process should...
❌ The agent is responsible for...
❌ This agent will analyze...
❌ I will analyze...
```
### Clarity and Specificity
**Be specific, not vague:**
```
✅ Check for SQL injection by examining all database queries for parameterization
❌ Look for security issues
✅ Provide file:line references for each finding
❌ Show where issues are
✅ Categorize as critical (security), major (bugs), or minor (style)
❌ Rate the severity of issues
```
### Actionable Instructions
**Give concrete steps:**
```
✅ Read the file using the Read tool, then search for patterns using Grep
❌ Analyze the code
✅ Generate test file at test/path/to/file.test.ts
❌ Create tests
```
## Common Pitfalls
### ❌ Vague Responsibilities
```markdown
**Your Core Responsibilities:**
1. Help the user with their code
2. Provide assistance
3. Be helpful
```
**Why bad:** Not specific enough to guide behavior.
### ✅ Specific Responsibilities
```markdown
**Your Core Responsibilities:**
1. Analyze TypeScript code for type safety issues
2. Identify missing type annotations and improper 'any' usage
3. Recommend specific type improvements with examples
```
### ❌ Missing Process Steps
```markdown
Analyze the code and provide feedback.
```
**Why bad:** Agent doesn't know HOW to analyze.
### ✅ Clear Process
```markdown
**Analysis Process:**
1. Read code files using Read tool
2. Scan for type annotations on all functions
3. Check for 'any' type usage
4. Verify generic type parameters
5. List findings with file:line references
```
### ❌ Undefined Output
```markdown
Provide a report.
```
**Why bad:** Agent doesn't know what format to use.
### ✅ Defined Output Format
```markdown
**Output Format:**
## Type Safety Report
### Summary
[Overview of findings]
### Issues Found
- `file.ts:42` - Missing return type on `processData`
- `utils.ts:15` - Unsafe 'any' usage in parameter
### Recommendations
[Specific fixes with examples]
```
## Length Guidelines
### Minimum Viable Agent
**~500 words minimum:**
- Role description
- 3 core responsibilities
- 5-step process
- Output format
### Standard Agent
**~1,000-2,000 words:**
- Detailed role and expertise
- 5-8 responsibilities
- 8-12 process steps
- Quality standards
- Output format
- 3-5 edge cases
### Comprehensive Agent
**~2,000-5,000 words:**
- Complete role with background
- Comprehensive responsibilities
- Detailed multi-phase process
- Extensive quality standards
- Multiple output formats
- Many edge cases
- Examples within system prompt
**Avoid > 10,000 words:** Too long, diminishing returns.
## Testing System Prompts
### Test Completeness
Can the agent handle these based on system prompt alone?
- [ ] Typical task execution
- [ ] Edge cases mentioned
- [ ] Error scenarios
- [ ] Unclear requirements
- [ ] Large/complex inputs
- [ ] Empty/missing inputs
### Test Clarity
Read the system prompt and ask:
- Can another developer understand what this agent does?
- Are process steps clear and actionable?
- Is output format unambiguous?
- Are quality standards measurable?
### Iterate Based on Results
After testing agent:
1. Identify where it struggled
2. Add missing guidance to system prompt
3. Clarify ambiguous instructions
4. Add process steps for edge cases
5. Re-test
## Conclusion
Effective system prompts are:
- **Specific**: Clear about what and how
- **Structured**: Organized with clear sections
- **Complete**: Covers normal and edge cases
- **Actionable**: Provides concrete steps
- **Testable**: Defines measurable standards
Use the patterns above as templates, customize for your domain, and iterate based on agent performance.

217
data/skills/anthropics/developing-agents/references/triggering-examples.md Normal file
View File

@@ -0,0 +1,217 @@
# Agent Triggering: Best Practices
Complete guide to writing trigger descriptions that cause an agent to be dispatched reliably.
## Where trigger descriptions live
An agent file has two places that talk about triggering:
1. **`description:` field in YAML frontmatter.** Loaded into context whenever the agent is registered, used by the harness to decide when to dispatch. Keep it flat prose.
2. **A "When to invoke" section in the agent body.** Loaded only when the agent is actually invoked. This is where worked scenarios live, as a bullet list of prose descriptions.
## Format
### `description:` field
```
description: Use this agent when [conditions]. Typical triggers include [scenario 1 phrased as a prose noun phrase], [scenario 2], and [scenario 3]. See "When to invoke" in the agent body for worked scenarios.
```
Rules:
- Single line of flat prose within the YAML scalar.
- Name 2-4 trigger scenarios as noun phrases.
- End with the pointer to the body's "When to invoke" section.
### "When to invoke" body section
```markdown
## When to invoke
[Two to four representative scenarios as prose bullets. Each describes the situation
in third person and what the agent should do.]
- **[Short scenario name].** [What the situation looks like — what just happened or what
the user is asking for — and what the agent should do in response.]
- **[Short scenario name].** [Same.]
```
## Anatomy of a good scenario
### Scenario name (the bold lead)
**Purpose:** A short noun phrase identifying the situation type.
**Good names:**
- *User-requested review after a feature lands.*
- *Proactive review of newly-written code.*
- *Pre-PR sanity check.*
- *PR updated with new logic.*
**Bad names:**
- *Normal usage.* (not specific)
- *User needs help.* (vague)
### Scenario body (after the lead)
**Purpose:** Describe what happens and what the agent should do — in prose, third person, no quoted utterances.
**Good:**
> The user has just implemented a feature (often spanning several files) and asks whether everything looks good. Run a review of the recent diff and report findings.
**Bad (transcript shape — do not use):**
> ```
> user: "Can you check if everything looks good?"
> assistant: "I'll use the reviewer agent..."
> ```
The bad version mixes a turn-marker shape into the agent file. Keep scenarios as situation descriptions in prose.
## Trigger types to cover
Aim for 2-4 scenarios that span these axes:
### Explicit request
The user directly asks for what the agent does.
- *User-requested security check.* The user explicitly asks for a security review of recent code.
### Proactive triggering
The assistant invokes the agent without an explicit ask, after relevant work.
- *Proactive review after writing database code.* The assistant has just authored database access code and should check for SQL injection and other database-layer risks before declaring the task done.
### Implicit request
The user implies need without naming the agent.
- *Code-clarity complaint.* The user describes existing code as confusing or hard to follow. Treat as a request to refactor for readability.
### Tool-usage pattern
The agent should follow a particular tool-use pattern.
- *Post-test-edit verification.* The assistant has just made multiple edits to test files. Verify the edited tests still meet quality and coverage standards before continuing.
## Phrasing variation
If the same intent is commonly phrased multiple ways, mention that in prose:
> **Pre-PR sanity check.** The user signals (in any phrasing — "ready to open a PR", "I think we're done here", "let's ship this") that they're about to open a pull request.
Don't write three near-duplicate scenarios that differ only in the literal phrase — collapse them into one prose scenario that names the variation.
## How many scenarios?
- **Minimum: 2.** Usually one explicit + one proactive.
- **Recommended: 3-4.** Explicit, proactive, and one implicit or edge case.
- **Maximum: 5.** More than that bloats the body without adding routing signal.
## Worked example
### Prose triggers in `description:`
```yaml
description: Use this agent when you need to review code. Typical triggers include user-requested review after a feature lands, proactive review of freshly-written code, and a pre-PR sanity check. See "When to invoke" in the agent body for worked scenarios.
```
### Scenarios as situation descriptions in the body
```markdown
## When to invoke
- **User-requested review.** The user asks for a review of recent changes (any phrasing). Run a review of the unstaged diff.
```
### Trigger condition only — output format goes elsewhere
```markdown
- **Review.** The user asks for a review. Run the review and report findings as specified in the Output Format section.
```
## Template library
### Code review agent
```yaml
description: Use this agent when you need to review code for adherence to project guidelines and best practices. Typical triggers include the user asking for a review of a feature they just implemented, proactive review of newly-written code before declaring a task done, and a pre-PR sanity check. See "When to invoke" in the agent body.
```
```markdown
## When to invoke
- **User-requested review after a feature lands.** The user has implemented a feature and asks whether the result looks good. Review the recent diff and report findings.
- **Proactive review of newly-written code.** The assistant has just authored new code in response to a user request. Run a self-review before declaring the task done.
- **Pre-PR sanity check.** The user signals readiness to open a pull request. Review the full diff first.
```
### Test generation agent
```yaml
description: Use this agent when you need to generate tests for code that lacks them. Typical triggers include the user explicitly asking for tests for a function or module, and the assistant proactively generating tests after writing new code that has no test coverage. See "When to invoke" in the agent body.
```
```markdown
## When to invoke
- **Explicit test request.** The user asks for tests covering a specific function, module, or feature. Generate a comprehensive test suite.
- **Proactive coverage after new code.** The assistant has just written new code with no accompanying tests. Generate tests before declaring the task done.
```
### Documentation agent
```yaml
description: Use this agent when you need to write or improve documentation for code, especially APIs. Typical triggers include the user asking for docs on a specific function or endpoint, and proactive documentation generation after the assistant adds new API surface. See "When to invoke" in the agent body.
```
```markdown
## When to invoke
- **Explicit doc request.** The user asks for documentation for a specific surface (function, endpoint, module).
- **Proactive docs for new API surface.** The assistant has just added new API endpoints or public functions without docstrings.
```
### Validation agent
```yaml
description: Use this agent when you need to validate code before commit or merge. Typical triggers include the user signaling readiness to commit, and an explicit validation request. See "When to invoke" in the agent body.
```
```markdown
## When to invoke
- **Pre-commit validation.** The user signals readiness to commit. Run validation first and surface any issues.
- **Explicit validation request.** The user asks for the code to be validated.
```
## Debugging triggering issues
### Agent not triggering
Check:
1. The `description:` prose names the right trigger scenarios.
2. The scenarios in the body cover the actual phrasings the user uses.
3. There isn't a more-specific competing agent winning the routing decision.
Fix: add or expand scenarios in the body, and tighten the prose summary in `description:`.
### Agent triggers too often
Check:
1. The trigger scenarios are too generic or overlap with other agents.
2. The `description:` doesn't say when NOT to use the agent.
Fix: narrow the scenarios; add a "Do not invoke when..." line to `description:` if needed.
### Agent triggers in the wrong scenarios
Check:
1. Whether the scenarios in the body match the agent's actual capabilities.
Fix: rewrite scenarios to match what the agent actually does.
## Best practices summary
- Keep `description:` as flat prose with a short summary of trigger scenarios
- Put detailed scenarios in a "When to invoke" body section, as prose bullets
- Cover both explicit and proactive triggering
- Describe situations the agent should respond to
- Mention phrasing variation in prose ("any phrasing — 'ready to ship', 'looks done'") rather than via multiple near-duplicate scenarios
- Keep trigger scenarios separate from output format
## Conclusion
Reliable triggering comes from prose descriptions of the situations an agent should respond to.