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 repo-orphansgit 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-orphans)<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-orphans"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-orphans/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-orphans"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-orphans.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 | $0.00019 | $0.00598 |
| Opus 5.5 | $0.00008 | $0.00239 |
| Sonnet 5.5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
repo-orphans scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex form of the
/repo:orphanscommand. Other commands appear as$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-orphans — Orphan Finder
Find files that appear to have no consumers — scripts nobody calls, data files nothing reads, build outputs without sources.
Usage
$repo-orphans # Full repo
$repo-orphans tools/ # Scope to subtree
$repo-orphans --type scripts # Only check scripts
What It Checks
1. Orphaned Scripts
Python/shell scripts in scripts/, tools/, or bin/ directories that are
not referenced by:
- Any other script, Makefile, package.json script, or CI config
- Any README or documentation
- Any skill/command file
Search for the script's basename across the repo. If zero references exist outside the file itself, it's likely orphaned.
2. Orphaned Data Files
YAML, JSON, CSV files that are not:
- Imported or read by any code
- Referenced in any README or documentation
- A recognized tool config (
.eslintrc,pyproject.toml, CI workflows, etc. — many configs are consumed by convention, not by reference)
3. Source/Output Mismatches
- Generated outputs (
.pdf,.html, compiled binaries) without a corresponding source (.tex,.md,.py, …) - Sources whose expected output is missing (may indicate a broken build)
.example/.samplefiles where the real file now exists
4. Empty Directories
Directories that contain no files (only subdirs or nothing at all).
Interaction
Present findings grouped by type. For each orphan, show:
- The file path and size
- What was searched for (e.g., "grepped for
extract.py— 0 references") - Suggested action: delete, move, or add a reference
Deleting an orphan is destructive and a judgment call — an "orphan" is often a
legitimate standalone file the user keeps deliberately — so unlike the safe-fix
commands this one never auto-acts. It reports and waits for your decision
(delete, move, or add a reference), with no --ask needed: report-and-wait
is the only mode.
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.
- 8d ago First seen · 68 lines · 19 tokens per session scan A 1cfe47cb1aa3
repo-orphans is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 598 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-orphans compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-orphansrjwalters/kicad-tools | Skill | 73 | yesterday | MIT | A | 19 | Claude Code, Codex |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 3d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 49 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 947 | 4d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.5k | yesterday | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 70 | Claude Code |