audit SKILL.md skillA

audit from rsaryev/tokendoctor is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rsaryev/tokendoctor/audit@git:20261104.862763a

Pins git:20261104.862763a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rsaryev/tokendoctor
Path
skills/audit/SKILL.md
Versions recorded
5
Latest version
git:20261104.862763a, committed Nov 4, 2026
First version recorded
Oct 25, 2026
Size
2,650 bytes
Repository stars
21
License
MIT

Audit this Claude Code setup for settings that waste tokens or silently do nothing.

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

Audit the Claude Code configuration for the current project (or `$ARGUMENTS` if given).

1. Run `tokendoctor-audit --json` (add `--project <dir>` when an argument was given). It is read-only
   and reports the Claude Code version, what it found, and a list of findings, each with a
   severity, an explanation and a documentation link.
2. Present the findings grouped by severity: errors first (settings that are wrong or ignored),
   then warnings, then info. For each, give one or two sentences in plain words and the doc link.
   Do not restate the whole detail text.
3. Be honest about limits: the audit checks configuration against documented behaviour. It does
   not measure savings, so state no percentages. Point to `/usage` (usage breakdown and
   recommendations) and `/context` (what is loaded now) for measuring.
4. Say which findings have an automatic fix (those with a `fixes` list) and offer
   `/tokendoctor fix <finding-id>` for them. Never edit files from this skill.
5. Review what Claude is told to do, not only how it is configured: read this project's memory
   (`~/.claude/projects/<project path with / as ->/memory/`, its `MEMORY.md` and the files it
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rsaryev/tokendoctor/audit@sha256:fc6891b717c724d0

The line at the top of this page pins the label git:20261104.862763a, 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_zvac5wh77ibc5duh.svg)](https://markdownregistry.com/a/art_zvac5wh77ibc5duh)

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

Versions

The registry has recorded 5 versions of this file, between Oct 25, 2026 and Nov 4, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261104.862763a latest2026-11-04 862763a 2,650 BA view · diff
git:20261103.fef7c932026-11-03 fef7c93 2,027 BA view · diff
git:20261101.f416dd52026-11-01 f416dd5 1,355 BA view · diff
git:20261025.012e9252026-10-25 012e925 1,357 BA view · diff
git:20261025.de9bf652026-10-25 de9bf65 1,360 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 (2650 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

rsaryev/tokendoctor · 21 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zvac5wh77ibc5duh
GET https://markdownregistry.com/api/v1/resolve?ref=rsaryev/tokendoctor/audit
GET https://markdownregistry.com/api/v1/blob/fc6891b717c724d04b1bad1dd2263ca164143ea82ec2ab57c08901d2ea762fda

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 rsaryev/tokendoctor

llms.txt@site/public llms.txt file
rsaryev/tokendoctor · site/public/llms.txt
git:20261101.f416dd5 · audit A · 21 stars
apply SKILL.md skill
rsaryev/tokendoctor · skills/apply/SKILL.md · Apply one tokendoctor audit fix after showing the exact change. Moved to /tokendoctor fix <id>, which needs no model…
git:20261101.f416dd5 · audit A · 21 stars
dashboard SKILL.md skill
rsaryev/tokendoctor · skills/dashboard/SKILL.md · Build and open a local dashboard of where your Claude Code tokens went, from every transcript on this machine.
git:20261104.862763a · audit A · 21 stars
optimize SKILL.md skill
rsaryev/tokendoctor · skills/optimize/SKILL.md · Look at token metrics, propose setting changes that cut waste, and apply the ones the person approves.
git:20261103.fef7c93 · audit A · 21 stars
sessions SKILL.md skill
rsaryev/tokendoctor · skills/sessions/SKILL.md · Measure where tokens actually went in recent Claude Code sessions, from the local transcripts.
git:20261103.fef7c93 · audit A · 21 stars

Every file in rsaryev/tokendoctor

Other files named audit

audit SKILL.md skill
pbakaus/impeccable · tests/oracle/workspaces/ctx-pin/.claude/skills/audit/SKILL.md · a user-authored audit skill
git:20260904.e2ff625 · audit B · 97,942 stars
audit SKILL.md skill
jeremylongshore/tons-of-skills-marketplace · plugins/ai-agency/hyperflow/skills/audit/SKILL.md · Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a…
v3.1.3 · audit A · 2,897 stars
audit SKILL.md skill
suboss87/fdeops · skills/audit/SKILL.md · Audit an inherited engagement or implementation against its evidence. Use when taking over work or joining mid-project…
git:20261005.ed7f271 · audit A · 947 stars
audit SKILL.md skill
jasonxudeveloper/nino · .claude/skills/audit/SKILL.md · Run an audit round of Nino with parallel agents in worktrees - layout, redundancy, code, core, security, performance…
git:20261030.3ec8ee8 · audit A · 652 stars
audit SKILL.md skill
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/audit/SKILL.md · Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when…
git:20261102.dc2618b · audit A · 572 stars
audit SKILL.md skill
educlopez/ui-craft · .agents/skills/audit/SKILL.md · Technical UI audit — a11y, performance, responsive. Produces a prioritized findings table. Invoke when the user asks…
git:20260725.d9710bc · audit A · 425 stars
audit SKILL.md skill
educlopez/ui-craft · .codex/skills/audit/SKILL.md · Technical UI audit — a11y, performance, responsive. Produces a prioritized findings table. Invoke when the user asks…
git:20260725.d9710bc · audit A · 425 stars
audit SKILL.md skill
skillmds/skillmd · plugins/cloud-devops/skills/audit/SKILL.md · Fast quality gate — detects stack, runs static analysis, checks cross-layer consistency, fixes issues. Run between…
v2.0.0 · audit A · 192 stars

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