Borrowing it
Nothing to install: this file belongs to richardwooding/file-search-on. 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/richardwooding/file-search-on/main/.claude/skills/open-source-prep/SKILL.mdgit clone --depth 1 https://github.com/richardwooding/file-search-onWrote 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/richardwooding/file-search-on/open-source-prep)<a href="https://agentmods.dev/skills/richardwooding/file-search-on/open-source-prep"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/open-source-prep/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/richardwooding/file-search-on/open-source-prep"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/open-source-prep.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 | $0.00154 | $0.01481 |
| Opus 5.5 | $0.00062 | $0.00592 |
| Sonnet 5.5 | $0.00031 | $0.00296 |
| Haiku 4.5 | $0.00015 | $0.00148 |
Grade A, and why
open-source-prep 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Source Prep
Walks a repository and reports what's missing before going public. Deterministic checks live in the audit script — the agent doesn't reinvent a checklist each time.
Quick start
# 1. Audit (read-only). Prints markdown punch-list.
python .claude/skills/open-source-prep/scripts/audit.py <repo-root>
# 2. For each gap, copy the template and customise.
cp .claude/skills/open-source-prep/templates/CONTRIBUTING.md.tmpl <repo-root>/CONTRIBUTING.md
# 3. For ambiguous decisions (which license? which CoC version?), open the
# matching reference file.
What the audit checks
| Area | Check |
|---|---|
| Legal | LICENSE / LICENSE.md present + SPDX detection |
| Discoverability | README.md exists, has install + usage sections, has license / build / version badges |
| Community | CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md, CHANGELOG.md |
| GitHub UX | .github/ISSUE_TEMPLATE/, .github/PULL_REQUEST_TEMPLATE.md, .github/dependabot.yml, .github/workflows/*.yml |
| Funding | FUNDING.yml — repo-level, or inherited from a public <owner>/.github repo. A repo-level file overrides the default outright; there is no merge, so a per-repo copy is only right when a repo needs a different target. An absent local file with a default present is reported as satisfied, not as a gap. |
| Hygiene | .gitignore, .editorconfig, .gitattributes |
| Repo metadata | gh repo view — description, homepage, topics, archived, has_issues |
| Secret scan | git history grep for .env, *.pem, *.key, credentials.json, id_rsa, common API-key patterns |
The audit is non-destructive — it never writes to the repo. It produces a markdown report and exits.
What the audit does NOT check
- Branch protection rules — requires admin perms on the repo. The audit notes that protection should be enabled for
main(require PR review, require status checks, no force-push) but doesn't query for it. - Code quality / test coverage — out of scope; the project's existing CI handles this.
- License compatibility of dependencies — dedicated tools (
go-licenses,license-checker,cargo-deny) do this better. - Vulnerability scan of dependencies — Dependabot / Snyk / Renovate do this in the repo. The audit just checks that Dependabot is configured.
What ships with it
6 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.
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.
- 1mo ago Changed · +1 lines 28a0c11bc5b1
- 2mo ago First seen · 77 lines · 154 tokens per session scan A 9c2fd97eff5b
open-source-prep is a skill published in the GitHub repository richardwooding/file-search-on (5 stars, last pushed 4d ago), licensed MIT. It adds 154 tokens to every session and 1,481 once invoked, about $0.0006 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.
open-source-prep compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| open-source-preprichardwooding/file-search-on | Skill | 5 | 4d ago | MIT | A | 154 | Claude Code |
| code-guidelines-godimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 124 | Claude Code, Codex |
| design-reviewdimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 30 | Claude Code, Codex |
| vhs-e2e-gifdimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 106 | Claude Code, Codex |
| agents-mddimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 138 | Claude Code, Codex |
| code-reviewpatriceckhart/zot | Skill | 359 | yesterday | MIT | A | 15 | Claude Code |
| code-review-pidimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 50 | Claude Code, Codex |