Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/rjwalters/kicad-tools/auditgit clone --depth 1 https://github.com/rjwalters/kicad-toolsWrote 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/commands/rjwalters/kicad-tools/audit)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/audit"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/audit.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.01042 |
| Opus 5 | $0.00010 | $0.00521 |
| Sonnet 5 | $0.00004 | $0.00208 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo:audit — Full Health Sweep
Run a full health sweep of the repository (or a specific subtree). Reports findings grouped by category and severity. Does not make changes — presents findings for discussion.
Usage
/repo:audit # Full repo
/repo:audit packages/core # Scope to one subtree
What It Checks
Run each of the following checks and compile results into a single report:
1. README Accuracy (see [[readme]])
- Browsable directory levels that lack a README (top-level and significant subdirs — so GitHub renders docs at each level someone navigates to)
- READMEs whose file/folder listings don't match actual contents
- Stale "gitignored" or "TODO" annotations that are no longer true
2. Orphaned Files (see [[orphans]])
- Scripts not referenced by any other file, Makefile, or CI config
- Data files (.yaml, .json, .csv) not imported or referenced anywhere
- Generated outputs (PDFs, binaries) without a corresponding source
3. Broken Links (see [[links]])
- Markdown links (
[text](path)) pointing to nonexistent files - CLAUDE.md paths that don't resolve
- Skill/command cross-references to missing files
- Links inside an install-template tree (an installer's
defaults/, a cookiecutter skeleton) resolve at their installed destination when the repo declares the mapping in.repo/link-roots.json. Fold [[links]]' mapping table into this report and say which mapping resolved a link — a mapping fails by hiding errors, so it has to show its work. With no declaration, resolution is unchanged. - A relative link that resolves outside the repo root (a citation into a
sibling repo in a multi-repo workspace) is checked against
.repo/link-siblings.jsonwhen the repo declares one. Report it distinctly:resolved via sibling repowhen the checkout is present and the target exists, a normalMISSINGfinding when the checkout is present but the target is gone, andsibling repo not present — unverifiable— neverMISSING— when the sibling isn't checked out on this machine at all. With no declaration, out-of-repo links are handled exactly as they are today.
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.
- 5d ago First seen · 109 lines · 20 tokens per session scan A cae6a3b64a3d
audit is a command published in the GitHub repository rjwalters/kicad-tools (55 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,042 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.