racecraft-plugins-public: Skill for Claude Code

.claude/skills/plugin-publish/SKILL.md

plugin-publish is a skill for Claude Code from racecraft-lab/racecraft-plugins-public. It costs 80 tokens per session (560 once invoked), scanned A, original, MIT.

A publishing workflow for plugin changes that checks the files, prepares a selected commit, sends it to the configured Git remote, and opens a pull request.

In plain words
What is it for?
Use it when you are ready to publish plugin changes for review. It is not intended for automated release version updates or certain documentation-only changes.
Why use it?
It reduces mistakes in the release process, such as invalid commit or pull-request titles, skipped checks, or accidentally including unrelated files.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md.

This is racecraft-lab/racecraft-plugins-public's own configuration. It tells Claude Code how to work on racecraft-plugins-public itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything racecraft-plugins-public configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/racecraft-lab/racecraft-plugins-public/main/.claude/skills/plugin-publish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-public

Made for: Claude Code.

Wrote 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.

agentmods badge for plugin-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/plugin-publish.svg)](https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/plugin-publish)
Your own site
<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>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 33a85704a0e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.claude/skills/plugin-publish/SKILL.md · 46 lines

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:

  1. Pre-flight checkpython3 tests/speckit-pro/run-all.py --layer 1 must pass (catches missing frontmatter and invalid JSON).
  2. Detect remotegit remote -v (per global CLAUDE.md "Git Operations" rule — don't assume origin).
  3. Stage selectively — list candidate files, ask user which to include. NEVER git add -A or git add ..
  4. Commit with conventional-commits prefix — required types: feat, fix, chore, docs, refactor, test. Validate before writing.
  5. Push and open PRgh pr create with the same prefix in the title (the validate-pr-title CI check enforces this).
  6. 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.json versions)
  • For docs-only PRs touching CLAUDE.md or README.md (the detect CI 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-verify to skip hooks
  • Never push to main directly (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
Changes

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.

  1. 6d ago First seen · 46 lines · 80 tokens per session scan A 33a85704a0e6

Subscribe to this mod's changes

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.

Related

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…

marconae/speq-skill · 0 tokens

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.

yugasun/aiops · 47 tokens

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…

addyosmani/agent-skills · 74 tokens

gsd-quick

Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.

open-gsd/gsd-core · 24 tokens

gsd-quick-batch

Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.

open-gsd/gsd-core · 27 tokens

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.

jnMetaCode/superpowers-zh · 65 tokens