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 OpenKnots/okcode --skill githubgit clone --depth 1 https://github.com/OpenKnots/okcodeWrote 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/openknots/okcode/github)<a href="https://agentmods.dev/skills/openknots/okcode/github"><img src="https://agentmods.dev/badge/skills/openknots/okcode/github/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/openknots/okcode/github"><img src="https://agentmods.dev/badge/skills/openknots/okcode/github.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 | $0.00014 | $0.00441 |
| Opus 5.5 | $0.00006 | $0.00176 |
| Sonnet 5.5 | $0.00003 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
github 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.
What it actually says
GitHub Skill
When to use this skill
- Use when the task involves GitHub repositories, pull requests, issues, review threads, or CI checks.
- Use when the answer should be grounded in live repository state rather than memory or inference alone.
- Use when the user needs repository context before making code or process decisions.
- Use when reviewing changes, triaging issues, or diagnosing failing GitHub Actions workflows.
What this skill does
- Uses GitHub as the source of truth for repository, PR, issue, and CI state whenever connector data is available.
- Optimizes for actionable review, triage, and debugging rather than generic summaries.
- Prioritizes bugs, regressions, missing tests, and concrete follow-ups during review tasks.
- Keeps findings tied to exact files, checks, PR metadata, or issue context when possible.
Implementation
- Start by identifying whether the task is about repository context, issue triage, PR review, CI debugging, or publishing changes.
- Pull the relevant GitHub metadata before making conclusions about state, authorship, status, or changed files.
- For PR review, focus first on behavioral regressions, correctness, risk, and validation gaps.
- For CI failures, inspect failing checks and logs before proposing a fix.
- For issue or project triage, summarize the operational state and the next concrete action.
- Ground conclusions in the observed GitHub data and clearly label any inference.
- When code changes are involved, connect review comments to precise file paths or changed surfaces.
Best practices
- Do not rely on stale assumptions when current GitHub data is available.
- Keep findings specific, evidence-based, and prioritized by severity.
- Prefer exact file references, check names, issue numbers, and PR identifiers.
- Separate repository facts from interpretation.
- Avoid noisy summaries when the user needs a clear next action.
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 First seen · 49 lines · 14 tokens per session scan A 675f4cfdcc3e
github is a skill published in the GitHub repository OpenKnots/okcode (24 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 441 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 2026-08-30.
Other skills, from other repositories
codeflow-maintainer
OpenClaw-only maintainer PR workflow modes and skills. For OpenCoven/coven PR creation, redirect to skills/pr-agent, the Coven PR Readiness Agent.
openclaw-dev
OpenClaw Dev Agent — OpenClaw-only docs-aware development assistant. For OpenCoven/coven PR creation, redirect to skills/pr-agent, the Coven PR Readiness Agent.
pr-agent
Coven PR Readiness Agent for assembling agent-ready OpenCoven pull requests. Use when preparing PR context, verification, risk, rollback, and handoff material for OpenCoven/coven.
pr-comment
Answer a maintainer's question about an open PR with concrete, code-cited evidence. The PR-side counterpart to issue-comment — for questions tied to the diff, not a full review.
review_rebase
Queue a review then rebase combo for a PR (ex: /rr https://github.com/owner/repo/pull/42).
ultrareview
Queue an ultra-thorough code review for a PR — architecture + silent-failure passes combined (ex: /ultrareview https://github.com/owner/repo/pull/42).