Borrowing it
Nothing to install: this file belongs to racecraft-lab/racecraft-plugins-public. 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/racecraft-lab/racecraft-plugins-public/main/.claude/skills/plugin-publish/SKILL.mdgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/racecraft-lab/racecraft-plugins-public/plugin-publish)<a href="https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/plugin-publish"><img src="https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/plugin-publish.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.00560 |
| Opus 5 | $0.00040 | $0.00280 |
| Sonnet 5 | $0.00016 | $0.00112 |
| Haiku 4.5 | $0.00008 | $0.00056 |
Grade A, and why
plugin-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 6d 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.
What it actually says
plugin-publish
User-invocable. Stops Claude from auto-running this — it has side effects (push, PR).
What this does
Walks through the publish flow documented in CLAUDE.md, but enforces the parts that are easy to forget:
- Pre-flight check —
python3 tests/speckit-pro/run-all.py --layer 1must pass (catches missing frontmatter and invalid JSON). - Detect remote —
git remote -v(per global CLAUDE.md "Git Operations" rule — don't assumeorigin). - Stage selectively — list candidate files, ask user which to include. NEVER
git add -Aorgit add .. - Commit with conventional-commits prefix — required types:
feat,fix,chore,docs,refactor,test. Validate before writing. - Push and open PR —
gh pr createwith the same prefix in the title (thevalidate-pr-titleCI check enforces this). - Remind user — after PR is merged (squash-only), tell them to run:
/plugin marketplace update racecraft-plugins-public
When NOT to use
- For a release (release-please handles version bumps automatically — do not manually edit
plugin.jsonversions) - For docs-only PRs touching
CLAUDE.mdorREADME.md(thedetectCI job skips test matrix anyway; just commit + push, no skill needed) - For the marketplace.json/release-please-config.json triplet — those have their own PreToolUse guard hook
Hard rules
- Never merge the PR (only humans merge — see global memory)
- Never use
--no-verifyto skip hooks - Never push to
maindirectly (branch protection blocks it; use a feature branch + PR) - Conventional-commit title format:
<type>(<scope>): <description>(scope optional)
Output
When complete, report:
- Branch name pushed
- PR URL
- The marketplace-update command the user needs to run post-merge
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.
- 6d ago First seen · 46 lines · 80 tokens per session scan A 33a85704a0e6
plugin-publish is a skill published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 560 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 2026-08-31.
Other skills, from other repositories
speq-git-discipline
Read-only git guardrails and the Conventional Commits reference — no history writes, verify changes before completing. Triggered by planner-agent, implementer-agent, implementer-expert-agent, and recorder-agent. The headless orchestrators speq-plan-pr and speq-implement-pr are the sole exception: they write git…
gitops
Git operations wrapper: sync, stage, commit, push. Generates Conventional Commits messages with .scratch artifact references. Use when the user says gitops, commit, push, sync code, or needs version control operations.
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.