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 sailingnaturali/claude-skills --skill oss-branch-protectiongit clone --depth 1 https://github.com/sailingnaturali/claude-skillsWrote 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/sailingnaturali/claude-skills/oss-branch-protection)<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/oss-branch-protection"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/oss-branch-protection/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/sailingnaturali/claude-skills/oss-branch-protection"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/oss-branch-protection.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 | $0.00092 | $0.00845 |
| Opus 5.5 | $0.00037 | $0.00338 |
| Sonnet 5.5 | $0.00018 | $0.00169 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
oss-branch-protection 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 2mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSS branch-protection template
One protection policy for every public, non-fork repo in an org, applied idempotently with a single script. The policy binds contributors, not the solo maintainer.
The policy
Applied to each repo's default branch:
| Setting | Value | Why |
|---|---|---|
enforce_admins |
false | The maintainer (admin) stays exempt — keeps a direct-commit-on-main + force-push-after-cleanup workflow. Everything below binds non-admins only. |
| Required status checks | the repo's CI gate, strict (branch up to date) |
No red-CI merges. |
| Required PR reviews | none | A solo maintainer can't self-approve, so requiring reviews would just block them. External contributors have no write access — they must PR anyway, and CI gates the merge. |
| Force-push / delete branch | blocked (non-admins) | Protects history. Admins bypass via enforce_admins: false. |
required_conversation_resolution |
true | PR threads resolve before merge. |
Key idea: enforce_admins: false is what makes a strict policy compatible with a
solo maintainer who commits directly. Contributors get the guardrails; the owner keeps
their flow. If your org has multiple committers and wants review enforcement, set
required_pull_request_reviews and enforce_admins: true instead.
Deriving the CI gate
Required-check names vary by CI, so the applier reads the checks reported on the default branch's latest commit and picks a stable gate:
- Prefer an aggregate gate if present (e.g. a
CI Statussummary job) — stable across matrix changes, unlike per-OS/per-version legs. - Otherwise require the remaining real checks (test matrix, scanners,
build). - Drop non-gating / unstable contexts: anything matrix-templated (
${{ … }}),dependabot,deploy,publish, and site-only jobs (crosspost,report-build-status,update-uv-graph). These either don't report onpull_requestor would wedge PRs waiting on a check that never runs. - No CI on the latest commit → uniform rules only, no required check. Add a
pull_request-triggered workflow first, then re-run to attach a gate.
What ships with it
1 file 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.
- 2mo ago First seen · 65 lines · 92 tokens per session scan A 5b2b82611530
oss-branch-protection is a skill published in the GitHub repository sailingnaturali/claude-skills (3 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 845 once invoked, about $0.0004 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 2026-09-07.
oss-branch-protection compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oss-branch-protectionsailingnaturali/claude-skills | Skill | 3 | 5d ago | MIT | A | 92 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 85k | 5d ago | 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 | today | MIT | A | 20 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 51 | Claude Code |
| comet-githubrpamis/comet | Skill | 3.3k | today | MIT | A | 72 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 2d ago | MIT | A | 51 | Claude Code, Codex |