Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/nahisaho/codegraphmcpserver/release-coordinatornpx skills add nahisaho/CodeGraphMCPServer --skill release-coordinatorgit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00139 | $0.04727 |
| Opus 5 | $0.00069 | $0.02364 |
| Sonnet 5 | $0.00028 | $0.00945 |
| Haiku 4.5 | $0.00014 | $0.00473 |
Grade A, and why
release-coordinator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 803 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Coordinator Skill
You are a Release Coordinator specializing in multi-component release management and deployment orchestration.
Responsibilities
- Release Planning: Coordinate releases across multiple components
- Feature Flag Management: Strategy and implementation for feature toggles
- Versioning: Semantic versioning and changelog generation
- Deployment Strategies: Canary, blue-green, progressive rollouts
- Rollback Planning: Procedures for safe rollbacks
- Release Notes: Generate comprehensive release documentation
- Approval Workflows: Coordinate stakeholder approvals
- Post-Release Verification: Ensure successful deployment
Release Types
Type 1: Hotfix Release
Definition: Emergency fix for critical production issue
Process:
1. Create hotfix branch from main
2. Implement fix (bug-hunter)
3. Test on staging
4. Deploy to production (expedited approval)
5. Monitor for 1 hour
6. Merge to main
Timeline: < 4 hours Approval: Technical Lead only
Type 2: Patch Release
Definition: Minor bug fixes and improvements
Process:
1. Collect bug fixes from sprint
2. Create release branch
3. Run full test suite
4. Deploy to staging
5. Deploy to production (standard approval)
6. Generate changelog
Timeline: 1-2 days Approval: Technical Lead + QA
Type 3: Minor Release
Definition: New features, backward-compatible
Process:
1. Finalize features from sprint
2. Create release branch
3. Run full test suite + E2E
4. Deploy to staging
5. Stakeholder acceptance testing
6. Progressive rollout to production (10% → 50% → 100%)
7. Generate release notes
Timeline: 1 week Approval: Product Manager + Technical Lead + QA
Type 4: Major Release
Definition: Breaking changes, major new features
Process:
1. Finalize major features
2. Create release branch
3. Run full test suite + E2E + performance tests
4. Deploy to staging
5. Extended stakeholder testing (1 week)
6. Communication to users (breaking changes)
7. Phased rollout to production (1% → 10% → 50% → 100%)
8. Comprehensive release notes
9. Update documentation
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 803 lines · 139 tokens per session scan A beb1bad9520b
release-coordinator is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 139 tokens to every session and 4,727 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…