war-review SKILL.md skillA
war-review from ljferrer/workauditrefine is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ljferrer/workauditrefine/war-review@git:20261029.79dc6a0Pins git:20261029.79dc6a0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ljferrer/workauditrefine
- Path
skills/war-review/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261029.79dc6a0, committed Oct 29, 2026
- First version recorded
- Sep 11, 2026
- Size
- 22,683 bytes
- Repository stars
- 11
- License
- MIT
Post-run telemetry and friction review for a completed /war run — reads the newest (or --run-pinned) run manifest under .claude/war/runs/, mines the referenced workflow transcripts for tokens and tool-call counts, tallies the run's cost/effort metrics and WAR-self-inflicted friction signals (rendering n/a for anything unsourceable, never fabricated), and offers ONE operator-confirmed issue on the plugin repo when friction is found; --scavenge reconstructs pre-manifest runs best-effort. Use…
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
# /war-review — run telemetry + friction report You turn a completed `/war` run into a **cost/effort report** and a **friction report**, and — only when friction is found and the operator confirms — file **one** issue on the WAR plugin repo. You read the **run manifest** `/war` accumulated (`.claude/war/runs/<runId>.json`) and mine the workflow transcripts it points at. You are **read-only apart from two writes**: the local review file (`.claude/war/runs/<runId>-review.md`, always saved) and the single operator-confirmed issue. Manifest field contract: [`../war/references/schemas.md`](../war/references/schemas.md) (§ Run manifest). The manifest is **telemetry, never resume input** — you consume it, you never repair the run from it (ADR 0008 ordering is git > issues > ledger, untouched here). **Two honesty invariants, non-negotiable:** - **Never fabricate a number.** Any metric whose source (manifest field or transcript artifact) is absent, deleted, or unparseable renders **`n/a`** — never an estimate, never a guess. Every mined metric degrades to `n/a` independently. - **Numbers are best-effort harness reads, not billing truth.** Token and tool-call counts come from …
Read the whole file at its exact version.
How to install
mdr add ljferrer/workauditrefine/war-review@sha256:f6c3ef2c127cf5dcThe line at the top of this page pins the label git:20261029.79dc6a0, 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_x62nhuk4kn7i4s43)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 11, 2026 and Oct 29, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261029.79dc6a0 latest | 2026-10-29 | 79dc6a0 | 22,683 B | A | view · diff |
| git:20261027.4dc7c80 | 2026-10-27 | 4dc7c80 | 22,671 B | A | view · diff |
| git:20261027.99b6514 | 2026-10-27 | 99b6514 | 22,679 B | A | view · diff |
| git:20261027.d88b6d3 | 2026-10-27 | d88b6d3 | 22,549 B | A | view · diff |
| git:20260911.5b9a133 | 2026-09-11 | 5b9a133 | 21,940 B | A | view |
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 (22683 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
ljferrer/workauditrefine · 11 stars · license MIT · pushed 2026-11-04 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_x62nhuk4kn7i4s43 GET https://markdownregistry.com/api/v1/resolve?ref=ljferrer/workauditrefine/war-review GET https://markdownregistry.com/api/v1/blob/f6c3ef2c127cf5dc357b92ff6ea3c592401389483e92ca2d1ff0ab20127ca4c9
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.