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 skills add cyanheads/git-mcp-server --skill release-and-publishgit clone --depth 1 https://github.com/cyanheads/git-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cyanheads/git-mcp-server/release-and-publish)<a href="https://agentmods.dev/skills/cyanheads/git-mcp-server/release-and-publish"><img src="https://agentmods.dev/badge/skills/cyanheads/git-mcp-server/release-and-publish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cyanheads/git-mcp-server/release-and-publish"><img src="https://agentmods.dev/badge/skills/cyanheads/git-mcp-server/release-and-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 78 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 84 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 84 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 99 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Prompt Injection · line 82 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
What 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 5.1 | $0.00083 | $0.01405 |
| Opus 5 | $0.00042 | $0.00702 |
| Sonnet 5 | $0.00017 | $0.00281 |
| Haiku 4.5 | $0.00008 | $0.00140 |
Grade A, and why
release-and-publish 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 9d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preconditions
This skill runs after git wrapup. By the time it's invoked:
package.jsonversion is bumpedserver.jsonversion is bumped (top-level + each package entry)CHANGELOG.mdhas a new entry for this version with a concrete date (never[Unreleased])- README badges and version-bearing files are in sync
- Release commit (
chore: release v<version>) exists - Annotated tag (
v<version>) exists locally - Working tree is clean
If any are missing, halt and tell the user to finish wrapup first. Do not attempt to redo wrapup work from inside this skill.
Failure Protocol
Stop on the first non-zero exit. No retries, no remediation from inside the skill. Report to the user:
- Which step failed
- The exact error output
- Which destinations already received the release (npm published? tag pushed?) so they know the partial state
The user fixes locally and re-invokes, or runs the remaining steps manually. Publishes hard-fail with "version already exists" if replayed — that's the signal the step already succeeded.
Steps
1. Sanity-check wrapup outputs
Read package.json → capture version. Read server.json → verify top-level version matches and every packages[].version matches. Then verify git state:
git status --porcelain # must be empty — clean working tree
git describe --exact-match --tags HEAD 2>&1 # must equal v<version>
git rev-parse --abbrev-ref HEAD # note the branch name
If working tree is dirty, HEAD isn't on v<version>, or server.json versions drift from package.json, halt.
2. Run the verification gate
All three must succeed:
bun run devcheck
bun run rebuild
bun test
Any non-zero exit → halt with the failing command's output.
devcheck runs lint + format + typecheck + bun audit. rebuild is a clean + bun build to catch build-time regressions devcheck alone can miss.
3. Push to origin
git push
git push --tags
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.
- 9d ago First seen · 145 lines · 83 tokens per session scan A 7a8500638382
release-and-publish is a skill published in the GitHub repository cyanheads/git-mcp-server (240 stars, last pushed 15d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,405 once invoked, about $0.0004 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
publish-release
Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.
release-notes
Writes user-facing release notes from a git commit range. Use when asked to draft release notes, a changelog entry, or "what's new" text for a release.
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts) and an annotated tag. Verify, commit, tag. Stops at "committed and tagged locally" — no push, no publish. The release-and-publish skill picks up from here. Distilled…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts) and an annotated tag. Verify, commit, tag. Stops at "committed and tagged locally" — no push, no publish. The release-and-publish skill picks up from here. Distilled…