Agent Setup Health Audit
tw93/Waza
Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.
Audit a Claude Code setup for token waste and context bloat.
Install Usage Audit
$ npx skills add Mathews-Tom/armory --skill usage-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Mathews-Tom/armory usage-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/usage-audit .claude/skills/usage-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "usage-audit" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/usage-audit into .claude/skills/usage-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "usage-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Mathews-Tom/armory/tree/main/skills/usage-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Mathews-Tom/armory --skill usage-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Mathews-Tom/armory usage-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/usage-audit .agents/skills/usage-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "usage-audit" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/usage-audit into .agents/skills/usage-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "usage-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Mathews-Tom/armory --skill usage-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Mathews-Tom/armory usage-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/usage-audit .cursor/skills/usage-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "usage-audit" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/usage-audit into .cursor/skills/usage-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "usage-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Mathews-Tom/armory.git --path skills/usage-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Mathews-Tom/armory --skill usage-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Mathews-Tom/armory usage-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/usage-audit .gemini/skills/usage-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "usage-audit" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/usage-audit into .gemini/skills/usage-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "usage-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Mathews-Tom/armory usage-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Mathews-Tom/armory --skill usage-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/usage-audit .github/skills/usage-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "usage-audit" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/usage-audit into .github/skills/usage-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "usage-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Mathews-Tom/armory --skill usage-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Mathews-Tom/armory usage-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/usage-audit .opencode/skills/usage-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "usage-audit" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/usage-audit into .opencode/skills/usage-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "usage-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
usage-audit- GitHub stars
- 328
- Token cost
- ~1.8k tokens
- SKILL.md length
- 868 words
- Files
- 2
- Skills in repo
- 80
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audit a Claude Code setup for token waste and context bloat.
- Works in 4 steps: Get /context Data → Audit What's Bloated → Score and Report → …
- : audit my context
- SKILL.md covers Step 1: Get /context Data, Step 2: Audit What's Bloated, Step 3: Score and Report and Step 4: Offer to Fix
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Usage Audit is an agent skill from Mathews-Tom/armory. Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `evals/cases.yaml`).
It sits in Agent Workflows, covering MCP servers and Agent instruction files. It works with Model Context Protocol. The repository describes itself as: Curated, production-grade skills for AI coding agents. Battle-tested workflows for developers who use AI seriously. The licence is MIT.
When your agent uses it
- : audit my context
- Tasks that involve MCP servers
- Tasks that involve Agent instruction files
Example prompts
- “audit my context”
- “usage audit”
- “token audit”
- “/usage-audit”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4594fb7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Usage Audit loads about 1.8k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 868 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Mathews-Tom/armory at commit 4594fb7, republished under its MIT licence (© Mathews-Tom). 868 words, ~1,825 tokens.
Download SKILL.mdSave it as
.claude/skills/usage-audit/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- usage-audit
- description
- Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
- metadata.version
- 1.0.0
- metadata.category
- review
- metadata.tags
- context, tokens, audit, claude-code, bloat
- metadata.difficulty
- intermediate
Usage Audit
Bloated context costs twice: you burn usage limits faster and output quality drops because models attend most to the start and end of context. This skill finds the waste and tells you what to cut.
Credit: adapted from the context-audit skill in the Claude Code Context
Cleanup Guide (2026). Armory port adds package-aware checks and treats the
scoring rubric as an overridable reference, not a verdict.
Step 1: Get /context Data
Check the conversation for recent /context output. If the user has not run
it in this session, ask:
"Run
/contextin this terminal and paste the output. I can't run slash commands myself — once I can see the breakdown I'll audit everything it flags."
STOP HERE. Do not proceed to Step 2 until real /context data is
available. The breakdown determines what to audit and in what order. Without
it, the audit is guessing. Output the message above and wait.
Step 2: Audit What's Bloated
Work the categories from largest to smallest in the /context output. Run
independent checks in parallel.
MCP Servers
Each connected server loads full tool definitions into context every turn
(~15,000-20,000 tokens each), whether you invoke a tool or not. Under Opus 4.7 this
figure can run 1.0–1.35× higher for the same schemas due to a tokenizer update —
prefer measured values from /context over these static estimates.
- Count configured servers in
settings.jsonand~/.claude/settings.json. - Report total MCP overhead from
/context. - Flag any server with a CLI equivalent (Playwright, GitHub, Google Workspace, Notion, Slack, etc.) — the CLI costs zero tokens when idle.
- Cross-reference installed armory packages: if
mcp-to-skillis installed, recommend it explicitly for the heaviest server.
CLAUDE.md Files
Read every CLAUDE.md in scope (project root, .claude/, ~/.claude/). For
each file: count lines, then test every rule against the five filters.
| Filter | Flag when... |
|---|---|
| Default | Claude already does this without being told ("write clean code", "handle errors") |
| Contradiction | Conflicts with another rule in the same or a different file |
| Redundancy | Repeats something already covered elsewhere |
| Bandaid | Added to fix one specific bad output, not improve outputs generally |
| Vague | Interpreted differently every time ("be natural", "use good tone") |
If a CLAUDE.md exceeds 200 lines, check for progressive-disclosure opportunities: rules that only apply to specific tasks (API conventions, deploy steps, testing) should move to reference files with one-line pointers from the core file. A lean CLAUDE.md under 200 lines with universal context is fine as a single file — do not split for the sake of splitting.
Rules Packages (armory-specific)
Armory rules/ packages load into every session like CLAUDE.md does — they
are the real silent base tax. Higher priority than skill bloat.
- Enumerate installed rules packages via
~/.claude/settings.jsonor the armory installer registry if present. - For each rules package, read its
RULE.mdbody, count lines, apply the same five filters. - Flag any rules package over 300 lines. These hit every turn.
Show full SKILL.md (394 more words)Show less
Installed Skills
Scan ~/.claude/skills/*/SKILL.md and any project-local skills. For each:
- Measure SKILL.md body lines only — do NOT count files under
references/,scripts/, orevals/. Those load on demand, not on trigger. Penalizing total package LOC misattributes cost. - Flag SKILL.md body > 200 lines (warn) or > 500 lines (critical).
- Run the five filters on skill instructions: restated goals, hedging ("you may want to"), synonymous instructions ("be concise" + "keep it short" + "don't be verbose").
- Frontmatter description audit: count words in each skill's
descriptionfield. Flag any over 60 words. Skill descriptions load into the router on every session and should be trigger-focused, not prose.
Settings
Check settings.json for these keys:
| Setting | Flag if | Recommended |
|---|---|---|
autocompact_percentage_override | Missing or > 80 | 75 |
env.BASH_MAX_OUTPUT_LENGTH | At default (30-50K) | 150000 |
File Permissions
Check permissions.deny in settings.json. If missing, inspect the project
and flag bloat directories that should be denied:
| If this exists... | Should deny... |
|---|---|
package.json | node_modules, dist, build, .next, coverage |
Cargo.toml | target |
go.mod | vendor |
pyproject.toml / requirements.txt | __pycache__, .venv, *.egg-info |
Step 3: Score and Report
The rubric below is a reference default, not gospel. A "reference" skill
that wraps a large CLI surface (e.g., github, agent-builder) may
legitimately exceed line thresholds — judge the body, not the file count.
Users can override any deduction in their project CLAUDE.md.
Score starts at 100. Deduct per issue:
| Issue | Points |
|---|---|
| CLAUDE.md > 200 lines | -10 |
| CLAUDE.md > 500 lines | -20 |
| Rules package > 300 lines (body) | -10 each |
| Per 5 rules flagged by filters | -5 |
| Contradictions between files | -10 |
Missing autocompact_percentage_override | -10 |
Missing BASH_MAX_OUTPUT_LENGTH override | -5 |
| Skill body > 200 lines | -5 each |
| Skill body > 500 lines | -10 each |
| Skill description > 60 words | -2 each |
| Per connected MCP server with CLI equivalent | -5 each |
No permissions.deny and bloat dirs exist | -10 |
Floor at 0. Output this format:
# Usage Audit
Score: {N}/100 [{CLEAN|NEEDS WORK|BLOATED|CRITICAL}]
## Context Breakdown (from /context)
{Paste the key numbers}
## Issues Found
### [{CRITICAL|WARNING|INFO}] {Category}
{What's wrong}
Fix: {One-line actionable fix}
### Rules to Cut
{Each flagged rule: quoted text, which filter, one-line reason}
### Conflicts
{Contradictions between files, with paths}
## Top 3 Fixes
1. {Highest-impact fix}
2. {Second}
3. {Third}Score labels: 90-100 CLEAN, 70-89 NEEDS WORK, 50-69 BLOATED, 0-49 CRITICAL. Severity: CRITICAL > 10pts, WARNING 5-10pts, INFO < 5pts.
Step 4: Offer to Fix
After the report, offer targeted fixes:
"Want me to apply any of these? I can:
- Add missing
settings.jsonkeys (autocompact_percentage_override,BASH_MAX_OUTPUT_LENGTH)- Add
permissions.denyrules for detected bloat directories- Show a cleaned-up CLAUDE.md diff with flagged rules removed
- Compress fat skill frontmatter descriptions
- Recommend specific MCP servers to disconnect this session"
Auto-apply the settings and permissions changes (safe, reversible). Show a diff and wait for confirmation before modifying any instruction file (CLAUDE.md, RULE.md, SKILL.md) — instruction edits are load-bearing and users need final say.
© Mathews-Tom, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/usage-audit of Mathews-Tom/armory.
- SKILL.md
- evals/cases.yaml
Open the folder on GitHubat commit 4594fb7
Compare with similar skills
Usage Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Usage Audit this skillMathews-Tom/armory | 328 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Agent Setup Health Audittw93/Waza | 7.2k | — | ~5.2k | Automated safety check: Notes | MIT | |
| Semantix GuideGnosil/semantix | 821 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Working With Claude Code Docsobra/superpowers-developing-for-claude-code | 142 | — | ~1.5k | Automated safety check: Pass | None | |
| Agnixagent-sh/agnix | 446 | — | ~874 | Automated safety check: Pass | Apache-2.0 | |
| Claude Docs Consultantcentminmod/my-claude-code-setup | 2.7k | — | ~959 | Automated safety check: Pass | MIT |
Similar skills
Semantix Guide
Gnosil/semantix
Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project…
Working With Claude Code Docs
obra/superpowers-developing-for-claude-code
Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.
Agnix
agent-sh/agnix
A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.
Claude Docs Consultant
centminmod/my-claude-code-setup
Consult official Claude Code documentation from code.claude.com using selective fetching.
Clawmem
yoloshii/ClawMem
ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring…
More from Mathews-Tom/armory
All 80 skills in this repoArchitecture Reviewer
Mathews-Tom/armory
Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports.
Concept To Image
Mathews-Tom/armory
Turn concepts into static HTML visuals exported as PNG or SVG files via HTML/CSS/SVG.
Watch
Mathews-Tom/armory
A skill your agent uses when analyzing an existing video URL or local recording: "watch this video", "analyze youtube video", "summarize this video", "youtube transcript", "find this moment", "what…
Code Refiner
Mathews-Tom/armory
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust.
Concept To Video
Mathews-Tom/armory
Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition.
Decision Map
Mathews-Tom/armory
Maps the unresolved architecture, policy, and scope decisions that must be answered before planning can start: one durable decision ticket per question on the issue tracker, typed and blocker-linked…
Related
Works with
Categories
Questions about Usage Audit
What does Usage Audit do?
Audit a Claude Code setup for token waste and context bloat. Usage Audit is an agent skill from Mathews-Tom/armory. Audit a Claude Code setup for token waste and context bloat.
When should I use Usage Audit?
Usage Audit fits situations like: : audit my context; tasks that involve MCP servers; tasks that involve Agent instruction files.
How do I install Usage Audit in Claude Code?
Run `npx skills add Mathews-Tom/armory --skill usage-audit -a claude-code`. Or copy the skill folder (skills/usage-audit in Mathews-Tom/armory) into .claude/skills/usage-audit in your project. Claude Code loads it when a task matches its description.
How do I install Usage Audit in Codex?
Run `npx skills add Mathews-Tom/armory --skill usage-audit -a codex`. Or copy the skill folder (skills/usage-audit in Mathews-Tom/armory) into .agents/skills/usage-audit in your project. Codex loads it when a task matches its description.
Can I use Usage Audit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Mathews-Tom/armory --skill usage-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/usage-audit, .gemini/skills/usage-audit, .github/skills/usage-audit and .opencode/skills/usage-audit in your project.
What does Usage Audit need to run?
SKILL.md names no scripts, command-line tools or credentials: Usage Audit is instructions for the agent only.
Does Usage Audit access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Usage Audit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Usage Audit use?
Usage Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Usage Audit use?
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Usage Audit?
Skills that share tags, products or a category with Usage Audit: Agent Setup Health Audit (tw93/Waza, 7.2k stars), Semantix Guide (Gnosil/semantix, 821 stars), Working With Claude Code Docs (obra/superpowers-developing-for-claude-code, 142 stars) and Agnix (agent-sh/agnix, 446 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Usage Audit?
Mathews-Tom (a GitHub user) maintains it in Mathews-Tom/armory, which has 328 GitHub stars. The repository holds 80 skills in this directory. The repository was last updated on October 6, 2026.
Source: Mathews-Tom/armory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.