release-audit SKILL.md skillB
release-audit from amirfish1/claude-command-center is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add amirfish1/claude-command-center/release-audit@git:20261009.a664025Pins git:20261009.a664025 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- amirfish1/claude-command-center
- Path
plugin/skills/release-audit/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261009.a664025, committed Oct 9, 2026
- Size
- 8,230 bytes
- Repository stars
- 212
- License
- a license file GitHub does not identify
Use right before cutting a release — it spawns ONE fresh sibling session via CCC that audits only the JUDGMENT gates a release script cannot check (does the changelog actually describe the diff, does the version bump match semver for what changed, do the docs mention the new user-visible feature, is anything uncommitted or half-shipped) and returns a GO / NO-GO with blockers. Advisory only; it never touches the release.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
Release-audit spawns a single fresh CCC session that reviews whether a pending release is *ready* — but only on the gates that need judgment, not the ones a script already enforces. The deterministic mechanics (version bump in lockstep, tag, build, notarize, appcast, brew formula) belong to `scripts/cut-release.sh` and should stay there; adding a session to re-run them just adds nondeterminism to the one place you want none. What a script can't judge is whether the changelog honestly describes the diff, whether the bump is the right *kind* of bump, and whether the docs caught up. That's this skill. It builds on the spawn/report_to mechanics in the `ccc-orchestration` skill — read that first for the full Spawn/Inject/Ask API. ## Cost **1 spawned session.** Each spawn is a real billed session on the user's kanban — tell the user the count before spawning. This is a pre-release gate, not a per-commit check — run it once when you're about to cut `vX.Y.Z`, not on every push. ## What it audits — and what it must NOT do The auditor is **read-only and advisory**. It returns a report; it changes nothing. Say this in the prompt explicitly, because a helpful session will …
Read the whole file at its exact version.
How to install
mdr add amirfish1/claude-command-center/release-audit@sha256:d58b0845718a6a8aThe line at the top of this page pins the label git:20261009.a664025, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_yfmufxomanwsmqr6)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 9, 2026.
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:8090)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8230 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
amirfish1/claude-command-center · 212 stars · license a license file GitHub does not identify · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yfmufxomanwsmqr6 GET https://markdownregistry.com/api/v1/resolve?ref=amirfish1/claude-command-center/release-audit GET https://markdownregistry.com/api/v1/blob/d58b0845718a6a8ad7e42de9506dc4ec755ceb801284f8bbd743fd1b9558f233
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from amirfish1/claude-command-center
Every file in amirfish1/claude-command-center