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 skills add rjwalters/kicad-tools --skill repogit 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/skills/rjwalters/kicad-tools/repo)<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo/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/rjwalters/kicad-tools/repo"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo.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 | $0.00025 | $0.07276 |
| Opus 5.5 | $0.00010 | $0.02910 |
| Sonnet 5.5 | $0.00005 | $0.01455 |
| Haiku 4.5 | $0.00003 | $0.00728 |
Grade F, and why
repo scanned grade F with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| [[sudo]] | Opt-in passwordless-sudo setup for a dev machine — install a `visudo`-validated `/etc/sudoers.d` drop-in (blanket `ALL` or a scoped command list) so an agent over SSH isn't blocked on password prompts; alway Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
download to a shell (`curl … | sh` — only when the pipe target *is* a Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Blocks** catastrophic operations outright: `rm -rf` of root / `$HOME` / a Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
download to a shell (`curl … | sh` — only when the pipe target *is* a How it starts
The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Skills
General-purpose tools for keeping a git repository healthy and productive. The
hygiene commands apply their safe, reversible fixes by default and report
each change; add --ask to review findings and confirm first. Anything
irreversible — deleting a branch, worktree, stash, or untracked file — is never
automatic: it takes an explicit opt-in and passes a permanent-loss check.
Commands whose only action is consequential (orphans, update-tools, deps,
followups, release, remote, browser, sudo) always confirm first by nature. The environment commands (remote, browser) stand up
infrastructure only after showing exactly what they will create and what it
costs.
Commands
| Command | What it does |
|---|---|
| [[help]] | Explain the installed /repo:* commands — what each does, where to start |
| [[all]] | The whole hygiene pass in order — audit, scrub, docs, tidy, update-tools, reset — safe fixes by default, destructive steps gated |
| [[audit]] | Full sweep — runs all hygiene checks, produces a summary report |
| [[scrub]] | Public-surface scrub — scan code, history, issues, PRs (and forks) for sensitive identifiers, and report which findings can actually be removed. Report-only; severity gates verbosity so it stays quiet inside [[all]]. Its fork-network sweep is implemented in scripts/repo/repo-scrub-forks.sh (installed to .claude/skills/repo/scripts/) |
| [[reset]] | Back to baseline — review stale worktrees/branches/stashes, sync with remote, return to the default branch |
| [[handoff]] | Roll the session safely — file follow-ups, reset, check for a CLI update, write a handoff note the next session reads first |
| [[tidy]] | Tidy up — build artifacts, caches, temp files, empty dirs |
| [[release]] | Cut a release — pre-flight, semver decision, CHANGELOG, version bump, tag, GitHub Release. Supports per-project release policy via named phase-boundary seams in .repo/release-policy.md |
| [[host-optimize]] | Prepare a Mac (or Linux box) for heavy Loom/agent build use — audit Gatekeeper churn, backup-agent interference, build-tree bloat; apply safe fixes, gate consequential ones |
| [[remote]] | Launch a cloud dev session (GCP or AWS) with this repo ready to go, then open SSH. Its provisioning contract is implemented once in scripts/repo/repo-remote.sh (installed to .claude/skills/repo/scripts/); the interactive flow delegates to that script, which also serves as a headless repo-remote up --yes --json entry point for non-interactive callers (e.g. loom's fleet add-worker) |
| [[browser]] | Check the environment's browser-automation stack — Browser Use CLI, official agent skill, auth, cloud credit/concurrency health — and offer confirm-gated installs; report-first, provisions only (never drives a browser) |
| [[sudo]] | Opt-in passwordless-sudo setup for a dev machine — install a visudo-validated /etc/sudoers.d drop-in (blanket ALL or a scoped command list) so an agent over SSH isn't blocked on password prompts; always confirmed first, validated with rollback on failure |
| [[update-tools]] | Check installed tool packages (Loom, Anvil, …) against their sources and offer updates |
| [[deps]] | Third-party dependency currency — reconcile organization policy, Dependabot-first setup with cooldown (Renovate opt-in), and bot PRs; report-only under --check |
| [[optimize-ci]] | Audit GitHub Actions for wasted CI minutes — change-relevance path filtering (required-check safe), cache keys, superseded runs; ranked by measured savings, report-only unless --apply. Its deterministic half is scripts/repo/repo-optimize-ci.py (installed to .claude/skills/repo/scripts/) |
| [[org-policy]] | Preview or deploy canonical rjwalters/repo preferences to the client's GitHub owner/.github repository through a policy PR |
| [[decide]] | Put operator decisions to the operator as ranked options — best to worst, each with why — so they can answer with a number |
| [[followups]] | Capture follow-on work from this session and file it as issues — here or in upstream tool repos, always confirmed first |
| [[branches]] | Branch & worktree hygiene — merged PRs, orphaned branches, stale worktrees |
| [[gitignore]] | Gitignore hygiene — over-ignored files, under-ignored build artifacts |
| [[docs]] | Documentation health — content accuracy, README structure, cross-references (canonical docs command) |
| [[links]] | Internal cross-references — markdown links, CLAUDE.md paths, skill graph |
| [[orphans]] | Files with no references — dead scripts, stale data, outputs without sources |
| [[readme]] | README accuracy vs actual directory contents |
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- install-metadata.json 391 B
- references/all.md 28 KB
- references/audit.md 5.1 KB
- references/branches.md 19 KB
- references/browser.md 6.9 KB
- references/decide.md 5.5 KB
- references/deps.md 80 KB
- references/docs.md 18 KB
- references/followups.md 40 KB
- references/gitignore.md 16 KB
- references/handoff.md 14 KB
- references/help.md 5.5 KB
- references/host-optimize.md 21 KB
- references/links.md 25 KB
- references/optimize-ci.md 23 KB
- references/org-policy.md 15 KB
- references/orphans.md 2.1 KB
- references/readme.md 4.9 KB
- references/release.md 50 KB
- references/remote.md 116 KB
- references/reset.md 9.4 KB
- references/scrub.md 21 KB
- references/sudo.md 21 KB
- references/tidy.md 52 KB
- references/update-tools.md 62 KB
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.
- 2d ago Changed · +1 lines 9fd9c32ed450
- 24d ago Changed 166c0220e5de
- 1mo ago Changed · +112 lines 8cee0b7ebd8e
- 2mo ago First seen · 332 lines · 25 tokens per session scan F 8988800a33ac
repo is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 7,276 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
repo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reporjwalters/kicad-tools | Skill | 73 | yesterday | MIT | F | 25 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 85k | yesterday | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | today | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 20 | Claude Code, Codex |
| comet-githubrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 72 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | 4d ago | MIT | A | 51 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 70 | Claude Code |