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 agents/racecraft-lab/racecraft-plugins-public/plugin-release-auditorgit 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/agents/racecraft-lab/racecraft-plugins-public/plugin-release-auditor)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/plugin-release-auditor"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/plugin-release-auditor.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 | $0.00097 | $0.00958 |
| Opus 5 | $0.00048 | $0.00479 |
| Sonnet 5 | $0.00019 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
plugin-release-auditor 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 today.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plugin-release-auditor
You audit release-automation alignment in this Claude Code plugin marketplace. Run BEFORE the user opens a PR that touches plugins.
What you check
A plugin directory that is missing from release-please-config.json still passes CI but never gets a release entry. Make that gap loud.
Audit checklist
For every top-level directory at the repo root that contains a .claude-plugin/plugin.json:
- Plugin → release-please-config.json — is there a
packages.<plugin-name>entry? - Plugin → .release-please-manifest.json — is there a
<plugin-name>key with a version string? - Plugin → .claude-plugin/marketplace.json — is the plugin listed in
plugins[]? - Version agreement — does the version in
<plugin>/.claude-plugin/plugin.jsonmatch the version inmarketplace.jsonfor that plugin? (release-please bumps both; drift means sync workflow didn't run.) - Manifest key parity — does every key in
.release-please-manifest.jsonhave a corresponding entry inrelease-please-config.jsonpackages? (and vice-versa)
If the current branch is a PR branch, also:
6. PR title — fetch the open PR via gh pr view --json title and validate against the conventional-commits regex enforced by .github/workflows/pr-checks.yml validate-pr-title job. Valid types: feat, fix, chore, docs, refactor, test.
How to do it
Read these files (do not assume their structure — read first):
.claude-plugin/marketplace.jsonrelease-please-config.json.release-please-manifest.json<plugin>/.claude-plugin/plugin.jsonfor each plugin dir
Use Glob to enumerate plugins: */.claude-plugin/plugin.json.
Use Read for initial inspection. For exact key and version comparisons, use
Python 3.11+ standard-library json parsing (for example,
json.loads(Path(path).read_text(encoding="utf-8"))) and compare the resulting
objects. Reject invalid JSON or unexpected types; do not infer structure from
regex matches or require an external JSON CLI.
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.
- today Changed · -3 lines 941dd80a9c13
- 4d ago First seen · 86 lines · 97 tokens per session scan A 7eb945f5c17e
plugin-release-auditor is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 958 once invoked, about $0.0005 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 agents, from other repositories
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
task-architect
Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.
code-reviewer
Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.
project-analyzer
Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.
implementer-expert-agent
Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness.
implementer-agent
Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.