github

A skill for inspecting live GitHub repositories, pull requests, issues, review discussions, and CI checks. GitHub is a service for hosting code and coordinating software work, while CI checks automatically build or test changes.

In plain words
What is it for?
Use it to review pull requests, investigate issues, diagnose GitHub Actions failures, inspect changed files, and understand repository or review context.
Why use it?
It grounds reviews and debugging in the repository’s current state rather than assumptions. It helps find concrete regressions, missing tests, failing checks, and follow-up work.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/openknots/okcode/github
Any agent
npx skills add OpenKnots/okcode --skill github
Clone the repo
git clone --depth 1 https://github.com/OpenKnots/okcode

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00441
Opus 5 $0.00007 $0.00220
Sonnet 5 $0.00003 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 2d ago against content hash 675f4cfdcc3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

packages/shared/src/skills-catalog/recommended/github/SKILL.md · 49 lines

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.
Changes

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.

  1. 2d ago First seen · 49 lines · 14 tokens per session scan A 675f4cfdcc3e

Subscribe to this mod's changes

github is a skill published in the GitHub repository OpenKnots/okcode (24 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 441 once invoked, about $0.0001 per session on Opus 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.