Borrowing it
Nothing to install: this file belongs to AnglerfishChess/chess-uci-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AnglerfishChess/chess-uci-mcp/main/.claude/skills/releasing/SKILL.mdgit clone --depth 1 https://github.com/AnglerfishChess/chess-uci-mcpWrote 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/anglerfishchess/chess-uci-mcp/releasing)<a href="https://agentmods.dev/skills/anglerfishchess/chess-uci-mcp/releasing"><img src="https://agentmods.dev/badge/skills/anglerfishchess/chess-uci-mcp/releasing/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/anglerfishchess/chess-uci-mcp/releasing"><img src="https://agentmods.dev/badge/skills/anglerfishchess/chess-uci-mcp/releasing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00104 | $0.01680 |
| Opus 5 | $0.00052 | $0.00840 |
| Sonnet 5 | $0.00021 | $0.00336 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
releasing scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Then confirm PyPI serves it — `curl -s https://pypi.org/pypi/chess-uci-mcp/json` should report `info.version` as How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release chess-uci-mcp
Release $1 — a bare semver such as 0.2.0, with no leading v, since the tag adds it.
The pipeline is: GitHub release → .github/workflows/publish.yml → PyPI via trusted publisher (OIDC, no tokens
anywhere) → the MCP registry, which the same workflow republishes. Everything below is what happens around that
trigger. Work through the steps in order and stop at the first failure instead of improvising past it: most of
these steps are cheap to retry, and the two that are not — the tag and the release — come last for that reason.
1. Check the preconditions
git status -sb— clean tree, onmain, in sync withorigin/main. Unpushed work either joins the release deliberately or waits; it must not ride along unnoticed.$1is unreleased: absent fromgit tag, and fromhttps://pypi.org/pypi/chess-uci-mcp/json.- Confirm a UCI engine is on PATH before trusting the tests:
command -v stockfish. This matters more here than in most projects, becausetests/test_engines.pyskips itself at module level when no engine is found — souv run pytestpasses having exercised nothing at all. A green run without that check is not evidence. - Then run them:
uv run pytest. gh run list --branch main --limit 1— CI green on HEAD. That job installs Stockfish itself, so it is the run that genuinely drove an engine, on a platform you do not develop on.
2. Bump the version
pyproject.toml holds the version; every other occurrence is a copy. Set version = "$1" there, let the lockfile
follow, then propagate it to chess_uci_mcp/__init__.py and to both version fields in server.json:
uv sync --extra=dev
uv run python ${CLAUDE_SKILL_DIR}/scripts/sync_version.py
Keep --extra=dev on that sync. A bare uv sync prunes the extras, quietly uninstalling pytest and ruff — which
step 1 just relied on, and which you will want again if anything below sends you back.
Commit it all as one change. The version in the code, in server.json and on the tag has to be a single string:
a wheel reporting a version its tag never had is a support puzzle, and a server.json naming a package version
PyPI does not serve is rejected by the registry outright.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 124 lines · 104 tokens per session scan A f2f53663090b
releasing is a skill published in the GitHub repository AnglerfishChess/chess-uci-mcp (2 stars, last pushed 6d ago), licensed MIT. It adds 104 tokens to every session and 1,680 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
release-changelog-harness
Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable. Use for release CI, install.sh, versioning, CHANGELOGs, shipping MCP/CLI without clone, or meta repos that only ship skills via npx…
polish-docs-meta
Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.
release-versioning
Discipline for release classification, version bumps, and changelogs, Conventional Commits classify the release range, SemVer computes the version from those commits, Keep a Changelog renders the result. Use when the user asks to cut a release, bump a version, write a changelog, decide if a change is a…
release-management
Tag a commit, publish a GitHub release, and read, correct or withdraw the tags and releases already there.
safe-deployment
Discipline for shipping changes reversibly, decouple deploy (code reaches production) from release (users see it) with feature flags, roll out progressively, and define the automated rollback trigger before shipping, not during the incident. Use when the user asks how to deploy a risky change, choose between…
close
Update version tracking when finishing work on a skill bundle. Use when you're done editing a skill project and need to bump version headers, recompute manifest hashes, update the changelog, flag stale files, or prepare a commit message. Triggers on: "close the session", "update versions", "save the bundle", "I'm done…