Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moberghr/mtk-agent-toolkit/main/.claude/skills/setup-audit/SKILL.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/setup-audit)<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/setup-audit"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/setup-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/setup-audit"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/setup-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.06595 |
| Opus 5.5 | $0.00011 | $0.02638 |
| Sonnet 5.5 | $0.00005 | $0.01319 |
| Haiku 4.5 | $0.00003 | $0.00660 |
Grade A, and why
setup-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MTK Setup Audit — Extract or Unify Architecture Principles
MTK File Resolution
Resolve MTK skill/reference/script paths per .claude/references/mtk-file-resolution.md unless the router already stated MTK_ROOT=<path> this session; CLAUDE.md, .claude/tech-stack, .claude/rules/, tasks/, docs/, .mtk/ stay project-relative.
Companion files: several steps below defer detail to .claude/references/audit-*.md companions, resolved via the block above. If a companion cannot be resolved at read time, stop the affected step and report the missing file path — do not reconstruct its content from memory.
This skill has two modes:
- Default (single-repo audit): Audit the current repository and produce
.claude/references/architecture-principles.mddescribing how this team builds software. --merge(multi-repo unification): Combine architecture audits from multiple repos placed under.claude/references/audits/into a single unified document.
Pick based on the argument. If the engineer passed --merge, jump to MERGE MODE below. Otherwise, run AUDIT MODE.
AUDIT MODE (default)
You are a senior architect performing an architectural audit of this repository. Document what the codebase ACTUALLY does, not what it should do. If you find inconsistencies, flag them as "⚠️ Inconsistency" — let the team decide which pattern to standardize on.
STEP -1: Versioned Re-Run Detection
Before regenerating anything, resolve whether this is a re-run and whether a previous template cache exists.
- Read current manifest version. The full manifest lives at the plugin root (marketplace installs have no project-local
.claude/manifest.json); target repos carry the slim.claude/mtk-version.jsonwritten bysetup-bootstrap:PM="${CLAUDE_PLUGIN_ROOT}/.claude/manifest.json" [ -f "$PM" ] || PM=".claude/mtk-version.json" CURRENT_VERSION=$(python3 -c "import json; print(json.load(open('$PM'))['version'])")
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · +4 lines 3f3bfed4a42a
- 1mo ago Changed · -7 lines 2fa1199e659d
- 1mo ago Changed 464f966bf6cf
- 2mo ago First seen · 340 lines · 27 tokens per session scan A 7cdb5ee00f13
setup-audit is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (9 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 6,595 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…