session-log-audit SKILL.md skillA
session-log-audit from markphelps/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add markphelps/skills/session-log-audit@git:20260812.60e1848Pins git:20260812.60e1848 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- markphelps/skills
- Path
development/skills/session-log-audit/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260812.60e1848, committed Aug 12, 2026
- Size
- 15,257 bytes
- Repository stars
- 6
- License
- MIT
Audit a project you build with AI agents by mining your own local agent session logs (Claude Code, Pi, Codex) for papercuts, bugs, and design flaws — the friction visible in what you actually typed rather than what the README claims. Use this when the user wants to find rough edges in their own tool or project, asks "what's annoying about X," wants to know why they keep working around their own software, is preparing a UX or DX pass on something they use daily, or wants to turn a week of agent…
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
# Session Log Audit A project's session logs are a more honest record of it than its README, its issues, or its author's memory. Where the user rephrases a command three times, the interface is wrong. Where they explain the same thing to an agent every session, the docs are wrong. Where they reach past the tool and do it by hand, the tool is wrong. None of that reaches the issue tracker, because in the moment it registers as friction rather than as a defect. This skill mines those logs into dated, receipted findings and a ranked fix list. It is deliberately evidence-first: the diagnosis comes after the collection, never alongside it. **Scope.** This works for a project the user builds _with_ agents and has worked on recently. It does not work on a project with no agent session history, and it is not a code review — it audits the gap between intent and lived experience, not correctness. ## Workflow Seven phases, 0 through 6, each with a gate. Never skip a phase. Never advance past a gate without meeting it. ### Phase 0 — Profile and intake First, **profile the project by inspection** (not by asking). Three attributes change the audit materially: …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_d6aerr65o766yuf4/492bfcf624ad9b6431b17831e10a106d7e11ef13a3ab105773fc7ee20a556104.json
Then /plugin install session-log-audit@markdownregistry-d6aerr65o766yuf4 in Claude Code. It installs git:20260812.60e1848, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add markphelps/skills/session-log-audit@sha256:492bfcf624ad9b64The line at the top of this page pins the label git:20260812.60e1848, 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_d6aerr65o766yuf4)
1 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in markphelps/skills/session-log-audit since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of session-log-audit from somewhere else? Ask it: where did my session-log-audit come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 1 version of this file, committed on Aug 12, 2026.
Watch this file (sign in, one email per new version)
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/session-log-audit/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (15257 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 link to a raw IP address
- pass: No script tag
Source
markphelps/skills · 6 stars · license MIT · pushed 2026-11-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_d6aerr65o766yuf4 GET https://markdownregistry.com/api/v1/resolve?ref=markphelps/skills/session-log-audit GET https://markdownregistry.com/api/v1/blob/492bfcf624ad9b6431b17831e10a106d7e11ef13a3ab105773fc7ee20a556104
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.