Skip to content

notque/vexjoy-agent / skills/meta/toolkit

toolkit

Verified

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

FileKindSize
SKILL.mdskill md15.5 KB
agents/skill-creator/analyzer.mdmarkdown4.8 KB
agents/skill-creator/comparator.mdmarkdown4.7 KB
agents/skill-creator/grader.mdmarkdown3.9 KB
assets/skill-creator/eval_viewer.htmlother57.1 KB
references/agent-comparison.mdmarkdown11.5 KB
references/agent-comparison/benchmark-tasks.mdmarkdown6.8 KB
references/agent-comparison/do-creation-compliance-tasks.jsonconfig8.5 KB
references/agent-comparison/examples-and-errors.mdmarkdown1.0 KB
references/agent-comparison/grading-rubric.mdmarkdown4.3 KB
references/agent-comparison/methodology.mdmarkdown7.4 KB
references/agent-comparison/optimization-guide.mdmarkdown12.0 KB
references/agent-comparison/optimization-tasks.example.jsonconfig853 B
references/agent-comparison/optimize-phase.mdmarkdown9.3 KB
references/agent-comparison/read-only-ops-short-tasks.jsonconfig375 B
references/agent-comparison/report-template.mdmarkdown3.8 KB
references/agent-comparison/socratic-debugging-body-short-tasks.jsonconfig372 B
references/agent-comparison/socratic-debugging-trigger-tasks.jsonconfig2.8 KB
references/agent-creator.mdmarkdown10.9 KB
references/agent-creator/agent-design-patterns.mdmarkdown12.4 KB
references/agent-creator/agent-eval-design.mdmarkdown7.7 KB
references/agent-creator/agent-frontmatter-template.mdmarkdown9.3 KB
references/agent-evaluation.mdmarkdown10.6 KB
references/agent-evaluation/batch-evaluation.mdmarkdown1.6 KB
references/agent-evaluation/common-issues.mdmarkdown2.1 KB
references/agent-evaluation/report-templates.mdmarkdown2.2 KB
references/agent-evaluation/scoring-rubric.mdmarkdown2.4 KB
references/blind-ab-tests.mdmarkdown7.8 KB
references/generate-claudemd.mdmarkdown11.0 KB
references/generate-claudemd/CLAUDEMD_TEMPLATE.mdmarkdown4.1 KB
references/generate-claudemd/examples-and-errors.mdmarkdown7.4 KB
references/github-profile-rules.mdmarkdown7.5 KB
references/github-profile-rules/github-api-patterns.mdmarkdown8.2 KB
references/github-profile-rules/rule-categories.mdmarkdown4.8 KB
references/hook-development.mdmarkdown10.9 KB
references/hook-development/architecture.mdmarkdown3.7 KB
references/hook-development/code-examples.mdmarkdown9.4 KB
references/hook-development/preferred-patterns.mdmarkdown6.5 KB
references/hook-development/telemetry-database.mdmarkdown6.5 KB
references/routing-table-updater.mdmarkdown10.2 KB
references/routing-table-updater/batch-mode.mdmarkdown2.1 KB
references/routing-table-updater/conflict-resolution.mdmarkdown3.8 KB
references/routing-table-updater/error-handling.mdmarkdown1.9 KB
references/routing-table-updater/examples.mdmarkdown4.8 KB
references/routing-table-updater/extraction-patterns.mdmarkdown2.2 KB
references/routing-table-updater/routing-format.mdmarkdown3.6 KB
references/routing-table-updater/skill-examples.mdmarkdown2.7 KB
references/skill-composer.mdmarkdown9.1 KB
references/skill-composer/compatibility-matrix.mdmarkdown13.0 KB
references/skill-composer/composition-patterns.mdmarkdown4.9 KB
references/skill-composer/examples.mdmarkdown17.1 KB
references/skill-composer/skill-patterns.mdmarkdown12.5 KB
references/skill-creator.mdmarkdown28.9 KB
references/skill-creator/agent-template.mdmarkdown18.5 KB
references/skill-creator/artifact-schemas.mdmarkdown8.2 KB
references/skill-creator/bundled-components.mdmarkdown2.3 KB
references/skill-creator/complexity-tiers.mdmarkdown8.0 KB
references/skill-creator/domain-research-targets.mdmarkdown13.2 KB
references/skill-creator/enrichment-workflow.mdmarkdown9.9 KB
references/skill-creator/error-catalog.mdmarkdown9.9 KB
references/skill-creator/preferred-patterns.mdmarkdown11.7 KB
references/skill-creator/progressive-disclosure.mdmarkdown8.5 KB
references/skill-creator/skill-template.mdmarkdown14.6 KB
references/skill-creator/workflow-patterns.mdmarkdown7.6 KB
references/system-upgrade.mdmarkdown11.0 KB
references/system-upgrade/component-audit-checklists.mdmarkdown8.4 KB
references/system-upgrade/upgrade-failure-modes.mdmarkdown8.7 KB
references/system-upgrade/upgrade-signal-parsing.mdmarkdown7.3 KB
references/toolkit-evolution.mdmarkdown14.5 KB
references/toolkit-evolution/diagnose-scripts.mdmarkdown9.5 KB
references/toolkit-evolution/evolution-history.mdmarkdown5.5 KB
references/toolkit-evolution/evolution-report-template.mdmarkdown716 B
references/toolkit-evolution/evolve-preferred-patterns.mdmarkdown6.9 KB
references/toolkit-evolution/evolve-scripts.mdmarkdown3.7 KB
references/toolkit-governance.mdmarkdown16.0 KB
references/toolkit-governance/adr-lifecycle.mdmarkdown10.9 KB
references/toolkit-governance/frontmatter-compliance.mdmarkdown11.1 KB
references/toolkit-governance/hook-standardization.mdmarkdown21.5 KB
references/toolkit-governance/routing-table-patterns.mdmarkdown11.6 KB
references/weak-model-uplift.mdmarkdown10.3 KB
scripts/agent-comparison/compare.pyscript2.3 KB
scripts/agent-comparison/generate_variant.pyscript19.6 KB
scripts/agent-comparison/optimize_loop.pyscript89.3 KB
scripts/agent-comparison/trigger_eval.pyscript19.5 KB
scripts/routing-table-updater/extract_metadata.pyscript10.8 KB
scripts/routing-table-updater/generate_routes.pyscript10.5 KB
scripts/routing-table-updater/scan.pyscript4.7 KB
scripts/routing-table-updater/update_routing.pyscript12.4 KB
scripts/routing-table-updater/validate.pyscript7.3 KB
scripts/skill-composer/build_dag.pyscript12.5 KB
scripts/skill-composer/discover_skills.pyscript12.1 KB
scripts/skill-composer/validate.pyscript12.3 KB
scripts/skill-creator/aggregate_benchmark.pyscript10.0 KB
scripts/skill-creator/eval_compare.pyscript10.2 KB
scripts/skill-creator/optimize_description.pyscript12.5 KB
scripts/skill-creator/package_results.pyscript7.8 KB
scripts/skill-creator/run_eval.pyscript6.3 KB

references/skill-composer/examples.md

View on GitHub
# Skill Composition Examples

Real-world examples of skill compositions with complete execution flows.

> **Note**: Scripts referenced below (`discover_skills.py`, `build_dag.py`, `validate.py`) are not yet implemented. These examples illustrate the intended workflow and expected output format.

## Example 1: Feature Development with Tests

### User Request
"Add rate limiting middleware to the API server with comprehensive tests"

### Skill Discovery Output
```bash
$ python3 ~/.claude/skills/toolkit/scripts/skill-composer/discover_skills.py \
    --skills-dir ./skills \
    --output /tmp/skill-index.json
```

```
Discovering skills in ./skills...
Found 18 potential skills
  ✓ workflow-orchestrator
  ✓ test-driven-development
  ✓ verification-before-completion
  ✓ comment-quality
  ✓ code-linting
  ... (13 more skills)

Building skill index...
Index written to: /tmp/skill-index.json

============================================================
SKILL INDEX SUMMARY
============================================================
Total skills: 18

Categories:
  workflow: 2
  testing: 2
  quality: 5
  documentation: 2
  code-analysis: 3
  debugging: 2
  other: 2

Skills with dependencies: 4
============================================================
```

### DAG Building Output
```bash
$ python3 ~/.claude/skills/toolkit/scripts/skill-composer/build_dag.py \
    --task "Add rate limiting middleware with comprehensive tests" \
    --skill-index /tmp/skill-index.json \
    --output /tmp/execution-dag.json
```

```
Analyzing task: Add rate limiting middleware with comprehensive tests

DAG written to: /tmp/execution-dag.json

============================================================
EXECUTION DAG
============================================================

Task: Add rate limiting middleware with comprehensive tests

Task Analysis:
  Primary goals: implementation
  Quality requirements: testing

Selected Skills (3): workflow-orchestrator, test-driven-development, verification-before-completion

Execution Plan:

Phase 1:
  → workflow-orchestrator

Phase 2:
  → test-driven-development

Phase 3:
  → verification-before-completion

Summary:
  Total phases: 3
  Parallel phases: 0
  Skills: 3
============================================================
```

### Validation Output
```bash
$ python3 ~/.claude/skills/toolkit/scripts/skill-composer/validate.py \
    --dag /tmp/execution-dag.json \
    --skill-index /tmp/skill-index.json
```

```
============================================================
SKILL COMPOSITION VALIDATION
============================================================

DAG Structure:
------------------------------------------------------------
  ✓ PASS - DAG has required field: task
  ✓ PASS - DAG has required field: phases
  ✓ PASS - DAG has required field: dependencies
  ✓ PASS - DAG has required field: execution_order
  ✓ PASS - Phases is a list
  ✓ PASS - Phase 1 numbered correctly
  ✓ PASS - Phase 2 numbered correctly
  ✓ PASS - Phase 3 numbered correctly

Acyclic Check:
------------------------------------------------------------
  ✓ PASS - DAG is acyclic (no circular dependencies)

Skill Existence:
------------------------------------------------------------
  ✓ PASS - Skill exists: workflow-orchestrator
  ✓ PASS - Skill exists: test-driven-development
  ✓ PASS - Skill exists: verification-before-completion

I/O Compatibility:
------------------------------------------------------------
  ✓ PASS - Compatibility: workflow-orchestrator → test-driven-development
  ✓ PASS - Compatibility: test-driven-development → verification-before-completion

Topological Ordering:
------------------------------------------------------------
  ✓ PASS - Dependency ordering: workflow-orchestrator → test-driven-development
  ✓ PASS - Dependency ordering: test-driven-development → verification-before-completion
  ✓ PASS - Topological ordering valid

============================================================
SUMMARY: 17/17 checks passed
         Composition valid - ready for execution
============================================================
```

### Execution Result
**Phase 1**: workflow-orchestrator created 4 subtasks:
1. Create rate limiter interface in `middleware/ratelimit.go`
2. Implement token bucket algorithm in `middleware/tokenbucket.go`
3. Add middleware registration in `server/server.go`
4. Add configuration in `config/config.go`

**Phase 2**: test-driven-development implemented each subtask:
- RED: Wrote failing tests for each subtask
- GREEN: Implemented minimum code to pass
- REFACTOR: Improved code quality

**Phase 3**: verification-before-completion validated:
- All tests pass (24/24)
- Code coverage: 94%
- Linting: 0 violations

**Total Duration**: 32 minutes

---

## Example 2: Debug with Documentation

### User Request
"Fix the authentication timeout issue and properly document the root cause"

### DAG Building Output
```
Task: Fix the authentication timeout issue and properly document the root cause

Task Analysis:
  Primary goals: debugging, documentation
  Quality requirements:

Selected Skills (2): systematic-debugging, comment-quality

Execution Plan:

Phase 1:
  → systematic-debugging

Phase 2:
  → comment-quality

Summary:
  Total phases: 2
  Parallel phases: 0
  Skills: 2
```

### Execution Result
**Phase 1**: systematic-debugging:
1. **Reproduce**: Created minimal test case triggering timeout
2. **Isolate**: Identified token validation as bottleneck
3. **Identify**: Found blocking HTTP call in hot path
4. **Verify**: Confirmed fix resolves timeout

**Phase 2**: comment-quality reviewed fix comments:
- Removed: "Fixed timeout bug on 2025-11-30"
- Replaced with: "Token validation uses async HTTP call to prevent blocking"
- Validated: Comments explain WHAT/WHY, not WHEN

**Total Duration**: 18 minutes

---

## Example 3: Parallel Quality Checks

### User Request
"Check code quality and documentation before creating PR"

### DAG Building Output
```
Task: Check code quality and documentation before creating PR

Task Analysis:
  Primary goals:
  Quality requirements: quality_checks

Selected Skills (3): code-linting, comment-quality, verification-before-completion

Execution Plan:

Phase 1 (PARALLEL):
  → code-linting
  → comment-quality

Phase 2:
  → verification-before-completion

Summary:
  Total phases: 2
  Parallel phases: 1
  Skills: 3
```

### Execution Result
**Phase 1 (Parallel)**:
- `code-linting` (6 seconds): Found 3 violations, auto-fixed 2, manual fix needed for 1
- `comment-quality` (4 seconds): Found 2 temporal references ("TODO: fix later", "Bug fixed yesterday")

**Phase 2**:
- `verification-before-completion`: All checks pass after manual fixes

**Total Duration**: 8 minutes (vs 12 minutes sequential = 33% time savings)

---

## Example 4: Research-Driven Implementation

### User Request
"Implement pagination following existing patterns in the codebase"

### DAG Building Output
```
Task: Implement pagination following existing patterns in the codebase

Task Analysis:
  Primary goals: implementation, analysis
  Quality requirements:

Selected Skills (4): pr-workflow (miner), codebase-analyzer, workflow-orchestrator, test-driven-development

Execution Plan:

Phase 1 (PARALLEL):
  → pr-workflow (miner)
  → codebase-analyzer

Phase 2:
  → workflow-orchestrator

Phase 3:
  → test-driven-development

Summary:
  Total phases: 3
  Parallel phases: 1
  Skills: 4
```

### Execution Result
**Phase 1 (Parallel)**:
- `pr-workflow (miner)` (15 seconds): Found 12 PR comments about pagination patterns
  - Tribal knowledge: "Always use cursor-based for large datasets"
  - Standard: "Limit parameter max value: 100"
- `codebase-analyzer` (12 seconds): Extracted pagination patterns from 3 existing implementations
  - Pattern: `page`, `limit`, `cursor` query parameters
  - Helper function: `pkg/pagination/cursor.go`

**Phase 2**:
- `workflow-orchestrator` created subtasks based on learned patterns:
  1. Add cursor-based pagination to handler
  2. Reuse `pkg/pagination/cursor.go` helper
  3. Enforce `limit <= 100` constraint
  4. Add integration tests

**Phase 3**:
- `test-driven-development` implemented following discovered patterns

**Total Duration**: 42 minutes
**Pattern Compliance**: 100% (followed all discovered conventions)

---

## Example 5: Language-Specific Quality Gate

### User Request
"Implement user preferences feature with appropriate quality checks"

### DAG Building (Go Project)
```
Task: Implement user preferences feature with appropriate quality checks

Task Analysis:
  Primary goals: implementation
  Quality requirements: quality_checks
  Domain hints: golang

Selected Skills (3): test-driven-development, go-patterns, verification-before-completion

Execution Plan:

Phase 1:
  → test-driven-development

Phase 2:
  → go-patterns

Phase 3:
  → verification-before-completion
```

### Execution Result
**Phase 1**: test-driven-development
- Implemented feature with tests
- All tests pass (RED → GREEN → REFACTOR)

**Phase 2**: go-patterns (Go-specific)
- golangci-lint: 0 violations
- go test -race: No race conditions
- go build: Successful
- Coverage: 89%

**Phase 3**: verification-before-completion
- All quality gates pass

**Total Duration**: 28 minutes

---

### Alternative: Python Project

**DAG Building (Python Project)**:
```
Selected Skills (3): test-driven-development, python-quality-gate, verification-before-completion
```

**Execution Result (Python)**:
**Phase 2**: python-quality-gate (Python-specific)
- ruff: 0 violations
- pytest: 15/15 tests passed, 92% coverage
- mypy: Type checking passed
- bandit: No security issues

**Total Duration**: 26 minutes

---

### Alternative: Multi-Language Project

**DAG Building (Multi-Language)**:
```
Selected Skills (3): test-driven-development, universal-quality-gate, verification-before-completion
```

**Execution Result (Multi-Language)**:
**Phase 2**: universal-quality-gate (Auto-detected)
- Detected languages: Go, JavaScript
- Go checks: golangci-lint passed, tests passed
- JavaScript checks: Biome passed, jest tests passed

**Total Duration**: 35 minutes

---

## Example 6: Documentation Audit

### User Request
"Audit and improve documentation quality across the codebase"

### DAG Building Output
```
Task: Audit and improve documentation quality across the codebase

Task Analysis:
  Primary goals: documentation, analysis
  Quality requirements:

Selected Skills (2): codebase-analyzer, comment-quality

Execution Plan:

Phase 1:
  → codebase-analyzer

Phase 2:
  → comment-quality

Summary:
  Total phases: 2
  Parallel phases: 0
  Skills: 2
```

### Execution Result
**Phase 1**: codebase-analyzer
- Analyzed 156 files
- Found 42 functions without documentation
- Identified 18 complex functions needing better docs

**Phase 2**: comment-quality
- Reviewed all comments
- Found 23 temporal references
- Suggested improvements for 31 comments

**Generated Report**:
```markdown
# Documentation Audit Report

## Statistics
- Total files: 156
- Undocumented functions: 42 (27%)
- Temporal references: 23
- Poor quality comments: 31

## High Priority Issues
1. `auth/token.go`: No package documentation
2. `server/handler.go`: 8 temporal references
3. `db/query.go`: Complex logic without explanation

## Recommendations
- Add package-level documentation
- Replace temporal references with explanations
- Document complex algorithms
```

**Total Duration**: 35 minutes

---

## Example 7: Loop Until Clean

### User Request
"Fix all linting violations in the payments module"

### DAG Building Output
```
Task: Fix all linting violations in the payments module

Task Analysis:
  Primary goals:
  Quality requirements: quality_checks

Selected Skills (1 with loop): code-linting

Execution Plan:

Loop (max 5 iterations):
  Phase 1:
    → code-linting

  If violations > 0:
    → fix violations
    → repeat
  Else:
    → exit loop

Summary:
  Total phases: 1 (looped)
  Skills: 1
```

### Execution Result
**Iteration 1**: code-linting found 18 violations
- Auto-fixed: 12
- Manual fix: 6

**Iteration 2**: code-linting found 4 violations (manual fixes created new issues)
- Auto-fixed: 3
- Manual fix: 1

**Iteration 3**: code-linting found 0 violations
- Loop exit: Clean!

**Total Duration**: 12 minutes
**Iterations**: 3/5

---

## Example 8: Style Compliance

### User Request
"Validate Go code meets team style guidelines before review"

### DAG Building Output
```
Task: Validate Go code meets team style guidelines

Task Analysis:
  Primary goals:
  Quality requirements: quality_checks
  Domain hints: golang

Execution Plan:

Phase 1:

Phase 2:
  → code-linting

Phase 3:
  → verification-before-completion

Summary:
  Total phases: 3
  Parallel phases: 0
  Skills: 3
```

### Execution Result
- Reviewability checks: Pass
- Maintainability checks: 2 violations
  - Long function (>50 lines) in `handler.go`
  - Deeply nested if statements in `validator.go`

**Phase 2**: code-linting (golangci-lint)
- 0 violations after team style fixes

**Phase 3**: verification-before-completion
- All checks pass

**Compliance Score**: 95/100 (A grade)

**Total Duration**: 14 minutes

---

## Error Recovery Examples

### Example 9: Failed Skill with Recovery

### User Request
"Add caching layer with tests"

### Initial Execution
```
Phase 1: workflow-orchestrator ✓
  Created 3 subtasks

Phase 2: test-driven-development ✗
  Error: Tests failed with 2 errors
  - Cache invalidation race condition
  - TTL configuration missing

Downstream impact:
  - verification-before-completion (blocked)

Recovery options:
  1. Fix test errors and retry
  2. Continue without tests (not recommended)
  3. Abort entire workflow
```

### Recovery Action
Selected option 1: Fix and retry

**Recovery Iteration**:
```
Phase 2 (retry): test-driven-development ✓
  Fixed race condition with mutex
  Added TTL configuration
  All tests pass (18/18)

Phase 3: verification-before-completion ✓
  All quality gates pass
```

**Total Duration**: 38 minutes (including 12 min recovery)

---

### Example 10: Circular Dependency Detection

### User Request
"Improve code quality comprehensively"

### Initial DAG Building
```
Analyzing task: Improve code quality comprehensively

✗ DAG validation failed: Circular dependency
  Cycle: code-linting → test-driven-development → code-linting

Solution: Remove circular dependency
  Option 1: Run code-linting → test-driven-development (no loop)
  Option 2: Run test-driven-development → code-linting (no loop)
  Option 3: Run both in parallel with verification after
```

### Corrected Composition
```
Selected Option 3: Parallel approach

Phase 1 (PARALLEL):
  → code-linting
  → test-driven-development

Phase 2:
  → verification-before-completion
```

---

## Advanced Composition Examples

### Example 11: Nested Composition

**High-level task**: "Implement microservice with full quality suite"

**Approach**: Use workflow-orchestrator to manage sub-compositions

```
workflow-orchestrator creates 3 major subtasks:

Subtask 1: Implement Core Service
  Composition: test-driven-development → code-linting

Subtask 2: Add API Documentation
  Composition: codebase-analyzer → comment-quality

Subtask 3: Quality Validation

Total Duration: 65 minutes
Skills Used: 7
```

---

### Example 12: Adaptive Composition

**Initial task**: "Add authentication feature"

**Initial composition**: test-driven-development → verification-before-completion

**Adaptive adjustment**: After phase 1, test coverage was only 45%

```
Adaptive decision:
  Insert additional iteration of test-driven-development

Modified composition:
  test-driven-development (iteration 1) →
  test-driven-development (iteration 2, focus on coverage) →
  verification-before-completion

Final coverage: 87%
Total Duration: 42 minutes (vs 30 minutes without adaptation)
```

---

## Performance Metrics

### Parallelization Benefits

| Composition | Sequential | Parallel | Savings |
|-------------|-----------|----------|---------|
| [code-linting, comment-quality] | 12 min | 8 min | 33% |
| [pr-workflow (miner), codebase-analyzer] | 28 min | 16 min | 43% |
| [3 language-specific lints] | 18 min | 8 min | 56% |

### Skill Chain Duration Averages

| Skills | Average Duration | Range |
|--------|-----------------|-------|
| 2 skills | 12 min | 8-18 min |
| 3 skills | 24 min | 18-35 min |
| 4 skills | 38 min | 30-50 min |
| 5+ skills | 52 min | 45-75 min |

---

## Usage Patterns

### Most Common Compositions (by frequency)

1. **workflow-orchestrator → test-driven-development** (45%)
2. **code-linting → verification-before-completion** (23%)
3. **systematic-debugging → comment-quality** (12%)
4. **[code-linting, comment-quality] → verification** (8%)
5. **pr-workflow (miner) → workflow-orchestrator** (5%)

### Success Rates

| Composition Pattern | Success Rate | Common Failure |
|-------------------|--------------|----------------|
| Simple sequential (2-3) | 96% | Test failures |
| Parallel quality checks | 92% | Linting violations |
| Research + implementation | 88% | Pattern mismatch |
| Loop until clean | 85% | Max iterations hit |
| Complex (5+) | 78% | Dependency issues |

---

These examples demonstrate real-world skill compositions with complete execution flows, error recovery, and performance characteristics. Use them as templates for your own compositions.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall