r-util-mem-audit SKILL.md skillA

r-util-mem-audit from rfxn/rdf is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rfxn/rdf/r-util-mem-audit@git:20260902.42a192d

Pins git:20260902.42a192d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rfxn/rdf
Path
adapters/claude-plugin/output/skills/r-util-mem-audit/SKILL.md
Versions recorded
1
Latest version
git:20260902.42a192d, committed Sep 2, 2026
Size
3,016 bytes
Repository stars
20
License
GPL-2.0

Stale memory and contradiction detection. Reads MEMORY.md files and.

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

# /rdf:r-util-mem-audit — Memory Fact-Check

Stale memory and contradiction detection. Reads MEMORY.md files and
cross-references every factual claim against live project state.
Read-only report — no modifications.

## Scope

- If CWD is a project directory: audit that project's MEMORY.md only
- If CWD is a workspace root (non-git parent of project repos): audit all project MEMORY.md files

MEMORY.md location:
`.rdf/memory/MEMORY.md`

## Protocol

### 1. Extract Claims

Read each MEMORY.md and extract verifiable factual claims:

**Version claims:**
- "Version: X.Y.Z" → verify against project source (grep VERSION=)
- "Branch: name" → verify against `git branch --show-current`

**Commit claims:**
- "HEAD: abc1234" → compare to `git rev-parse --short HEAD`
- Any commit hash mentioned → verify with `git log --oneline | grep`

**Test claims:**
- "N tests" → verify with `grep -rc '@test' tests/*.bats | awk`
- "all targets green" → check `gh run list --limit 1` if available

**Status claims:**
- Phase status markers → cross-reference PLAN.md
- "COMPLETE" markers → verify commits exist

**File/function claims:**
- "New function: name()" → verify presence in source
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rfxn/rdf/r-util-mem-audit@sha256:e849926988b787aa

The line at the top of this page pins the label git:20260902.42a192d, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_e2t5nx4g775jasjh.svg)](https://markdownregistry.com/a/art_e2t5nx4g775jasjh)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 2, 2026.

versioncommittedcommitsizeaudit
git:20260902.42a192d latest2026-09-02 42a192d 3,016 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3016 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

GitHub

rfxn/rdf · 20 stars · license GPL-2.0 · pushed 2026-10-28 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_e2t5nx4g775jasjh
GET https://markdownregistry.com/api/v1/resolve?ref=rfxn/rdf/r-util-mem-audit
GET https://markdownregistry.com/api/v1/blob/e849926988b787aae44fc015ade45564d40df6efe8304518f3419396de8708ba

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 rfxn/rdf

CLAUDE.md CLAUDE.md file
rfxn/rdf · CLAUDE.md
git:20261024.f212cfc · audit A · 20 stars
AGENTS.md@adapters/agents-md/output AGENTS.md file
rfxn/rdf · adapters/agents-md/output/AGENTS.md
git:20261026.290fa1c · audit A · 20 stars
r-audit-slop SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-audit-slop/SKILL.md · AI slop audit. Finds dead code, orphan helpers, noop functions,
git:20260902.42a192d · audit A · 20 stars
r-audit SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-audit/SKILL.md · Use when you want a full codebase audit: dispatches parallel reviewer and QA passes across the tree.
git:20261024.45c1549 · audit A · 20 stars
r-build SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-build/SKILL.md · Use when a plan exists and you want it built: dispatches the plan-execution orchestrator (engineer/QA/review gates) per…
git:20260925.864fc3d · audit A · 20 stars
r-context-audit SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-context-audit/SKILL.md · Measure, score, and report on Claude Code context overhead for this
git:20260902.42a192d · audit A · 20 stars
r-env SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-env/SKILL.md · Use to assess the environment against an optimal Claude Code + RDF setup: code intelligence plugins and language…
git:20261028.497294f · audit A · 20 stars
r-init SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-init/SKILL.md · Use to initialize RDF governance on a new or existing repository.
git:20261024.1352e8e · audit A · 20 stars
r-mode SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-mode/SKILL.md · Switch the operational mode for the current session.
git:20260902.42a192d · audit A · 20 stars
r-plan SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-plan/SKILL.md · Use when a spec is ready and you need an execution-grade, phase-by-phase implementation plan a fresh engineer can run…
git:20260924.c9abbec · audit A · 20 stars
r-refresh SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-refresh/SKILL.md · Use when the codebase has drifted from its governance docs and you want them re-derived from source.
git:20260902.42a192d · audit A · 20 stars
r-review-answer SKILL.md skill
rfxn/rdf · adapters/claude-plugin/output/skills/r-review-answer/SKILL.md · Route every finding in a sentinel or challenge report to a structured
git:20260902.42a192d · audit A · 20 stars

Every file in rfxn/rdf

Browse by kind, by grade A, or by owner.