context-audit SKILL.md skillA

context-audit from rezzminator/professor is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rezzminator/professor/context-audit@git:20261023.db16bb6

Pins git:20261023.db16bb6 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rezzminator/professor
Path
templates/global/skills/context-audit/SKILL.md
Versions recorded
1
Latest version
git:20261023.db16bb6, committed Oct 23, 2026
Size
7,117 bytes
Repository stars
9
License
MIT

USER-ONLY — /context-audit [project dir] [--engine claude|codex|opencode|all] [--loop main|{agent}] [--days N]: every layer a loop receives before its first tool call, rebuilt from disk and reconciled with its last real session; cut lines, duplicates, never-used items. Returns a table ranked by tokens reclaimed, then applies your rulings.

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

# context-audit

Arguments: project dir defaults to the working directory, `--engine` to `claude` (`all` runs claude, codex and opencode in turn), `--loop` to `main` (an agent name audits that sub-agent), `--days` to 30. Every number in the report comes from this run's output; `/context` is a user-only command, so the audit never asks for it.

## 1 Assemble and measure

Run, per engine, the path written in full, after `mkdir -p /tmp/context-audit`:

`python3 -I $HOME/.claude/skills/context-audit/context-audit.py {project dir} --engine {engine} --loop {loop} --days {N} > /tmp/context-audit/{engine}-{loop}.tsv`

It prints tab-separated lines, each opened by its kind:

- `PROBE`: a file or setting looked for, `found` or `absent`.
- `LAYER`: kind, bytes, ~tokens, status, uses in the window, source, name. Status: `LOADED` (its text is in the recorded first request), `DIFFERS` (loaded, but the recorded text differs from disk: cut, or a copy cached before an edit), `CHANGED-SINCE` (file newer than that session), `NOT-LOADED`, `HIDDEN (visibility:)`, `SHADOWED`, `DUPLICATE NAME`, `UNVERIFIED` (the engine records no request text), `NOT-ON-WIRE` (a harness block absent from that request).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rezzminator/professor/context-audit@sha256:d4c16d4e4d999ad1

The line at the top of this page pins the label git:20261023.db16bb6, 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_zckydeo233kzt4e7.svg)](https://markdownregistry.com/a/art_zckydeo233kzt4e7)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 23, 2026.

versioncommittedcommitsizeaudit
git:20261023.db16bb6 latest2026-10-23 db16bb6 7,117 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 (7117 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

rezzminator/professor · 9 stars · license MIT · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zckydeo233kzt4e7
GET https://markdownregistry.com/api/v1/resolve?ref=rezzminator/professor/context-audit
GET https://markdownregistry.com/api/v1/blob/d4c16d4e4d999ad1e9b7118a46c5bbb2001c419ca42e1a226b551cfe04d1a0b7

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 rezzminator/professor

CLAUDE.md CLAUDE.md file
rezzminator/professor · CLAUDE.md
git:20261031.33b149b · audit A · 9 stars
CLAUDE.md@pfm CLAUDE.md file
rezzminator/professor · pfm/CLAUDE.md
git:20261029.f2ffa89 · audit A · 9 stars
CLAUDE.md@plugins CLAUDE.md file
rezzminator/professor · plugins/CLAUDE.md
git:20261028.c38ea74 · audit A · 9 stars
chatlog SKILL.md skill
rezzminator/professor · templates/global/skills/chatlog/SKILL.md · Digests and prices agent runs — "what did that agent do", "where did the tokens go", "what does model X cost"; Claude…
git:20261029.85dea71 · audit A · 9 stars
codeprobe SKILL.md skill
rezzminator/professor · templates/global/skills/codeprobe/SKILL.md · Internal kit of collector — codeprobe.py copies code verbatim for numbered orders and prints their manifest. Not…
git:20261009.881ab88 · audit A · 9 stars
done-herewith SKILL.md skill
rezzminator/professor · templates/global/skills/done-herewith/SKILL.md · USER-ONLY Finishes a chat completely — /done-herewith: sweeps open threads, unfinished or unverified work, uncommitted…
git:20261026.5bfa612 · audit A · 9 stars
dude SKILL.md skill
rezzminator/professor · templates/global/skills/dude/SKILL.md · Course-corrects you on the user''s anger — `/dude [what went wrong]`, typed instead of an insult, or whenever the user…
git:20261018.0b15481 · audit A · 9 stars
lander-inventory SKILL.md skill
rezzminator/professor · templates/global/skills/lander-inventory/SKILL.md · Internal kit of flights-lander — lander-inventory.py lists what a diff left behind (LEFT, LITERAL, GONE rows) and…
git:20261023.b99e150 · audit A · 9 stars
tracetree SKILL.md skill
rezzminator/professor · templates/global/skills/tracetree/SKILL.md · Internal kit of tracer and sub-tracer — tracetree.py opens a trace run, stores each node's hops once, waits for the…
git:20261018.4bfcd8c · audit A · 9 stars
ultimate SKILL.md skill
rezzminator/professor · templates/global/skills/ultimate/SKILL.md · Pushes past the model's standard — `/ultimate [work]` on the named work or the work in hand, and whenever the ultimate…
git:20261018.d8a774a · audit A · 9 stars
legal SKILL.md skill
rezzminator/professor · templates/project/skills/legal/SKILL.md · Index of curated legal/compliance playbooks — DPA (Art. 28), DPIA (Art. 35), breach response (Art. 33/34), privacy…
git:20261023.35a6a72 · audit A · 9 stars

Every file in rezzminator/professor

Other files named context-audit

context-audit SKILL.md skill
garrytan/gbrain · plugin-variants/gbrain-coding/skills/context-audit/SKILL.md · Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the…
v1.0.0 · audit A · 31,463 stars
context-audit SKILL.md skill
garrytan/gbrain · plugin/skills/context-audit/SKILL.md · Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the…
v1.0.0 · audit A · 31,463 stars
context-audit SKILL.md skill
garrytan/gbrain · skills/context-audit/SKILL.md · Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the…
v1.0.0 · audit A · 31,463 stars
context-audit SKILL.md skill
undefined-ui/second-brain-os · plugins/agents-course/skills/context-audit/SKILL.md · Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to…
git:20261007.c7fa35b · audit A · 1,177 stars
context-audit SKILL.md skill
jpeetz/agent-skills · skills/development/finding-unknowns/skills/context-audit/SKILL.md · Use when agent context is bloated or contradictory.
v1.0.0 · audit A · 15 stars
context-audit SKILL.md skill
nordz0r/skills · plugins/all-skills/skills/context-audit/SKILL.md · Audit agent context composition, token budgets, and static versus dynamic inflation across system prompts, tool…
v1.0.0 · audit A · 8 stars
context-audit SKILL.md skill
nordz0r/skills · plugins/ai-tools/skills/context-audit/SKILL.md · Audit agent context composition, token budgets, and static versus dynamic inflation across system prompts, tool…
v1.0.0 · audit A · 8 stars
context-audit SKILL.md skill
nordz0r/skills · context-audit/SKILL.md · Audit agent context composition, token budgets, and static versus dynamic inflation across system prompts, tool…
v1.0.0 · audit A · 8 stars

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