Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rjwalters/kicad-toolsnpx agentmods add skills/rjwalters/kicad-tools/repo-linksWrote 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-links)<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-links"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-links/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-links"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-links.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 | $0.00021 | $0.06133 |
| Opus 5.5 | $0.00008 | $0.02453 |
| Sonnet 5.5 | $0.00004 | $0.01227 |
| Haiku 4.5 | $0.00002 | $0.00613 |
Grade A, and why
repo-links scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex form of the
/repo:linkscommand. Other commands appear as$repo-<verb>skills. Helper scripts and.claude/paths below are relative to the repository root and exist when the Claude Code surface is installed alongside this one.
$repo-links — Link Checker
Validate that internal cross-references across the repo actually resolve. Catches broken links from reorganization, renames, and deletions.
This is the cross-reference layer of [[docs]]. Use it directly when that's all you want to check; use [[docs]] for the full documentation sweep.
Usage
$repo-links # Full repo — fix unambiguous links, report as you go
$repo-links CLAUDE.md # Check one file
$repo-links .claude/ # Check skill/command files
$repo-links --ask # Review findings and confirm before fixing
What It Checks
1. Markdown Links
Scan all .md files for [text](path) links where path is a relative file
path (not a URL). Verify the target exists on disk.
Strip code before scanning. Remove fenced blocks and inline code spans from
the text first — a [text](path) inside backticks is a description of a link,
not a link:
text = re.sub(r'```.*?```', '', text, flags=re.S) # fenced blocks
text = re.sub(r'`[^`]*`', '', text) # inline spans
Without this the checker flags the sentences in this very file, and in [[audit]], that explain what it looks for. A checker that reports its own documentation as broken is not a checker anyone keeps running.
Skip:
- External URLs (http://, https://)
- Anchor-only links (#section)
- Image URLs from external services
Resolve against two bases, and only report a link that fails both. A relative path can legitimately be written against either the file's own directory or the repo root, and both conventions are in active use:
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 0f3e08da84ba
- 8d ago First seen · 510 lines · 21 tokens per session scan A 48f29dabf669
repo-links is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 6,133 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 2026-11-01.
repo-links compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-linksrjwalters/kicad-tools | Skill | 73 | yesterday | MIT | A | 21 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |