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 bntvllnt/agent-skills --skill githubgit clone --depth 1 https://github.com/bntvllnt/agent-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/bntvllnt/agent-skills/github)<a href="https://agentmods.dev/skills/bntvllnt/agent-skills/github"><img src="https://agentmods.dev/badge/skills/bntvllnt/agent-skills/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/bntvllnt/agent-skills/github"><img src="https://agentmods.dev/badge/skills/bntvllnt/agent-skills/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 | $0.00131 | $0.00907 |
| Opus 5.5 | $0.00052 | $0.00363 |
| Sonnet 5.5 | $0.00026 | $0.00181 |
| Haiku 4.5 | $0.00013 | $0.00091 |
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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub
GitHub operations via gh.
Router
| User says | Load reference | Do |
|---|---|---|
| help / gh help / flags / options | references/cli-help.md |
show CLI help safely |
| auth / login / token | references/auth.md |
authenticate gh |
| repo / clone / fork / sync | references/repo.md |
repository operations |
| issue / issues | references/issue.md |
issue triage and management |
| pr / pull request / review | references/pr.md |
PR create/review/merge workflows |
| actions / workflow / run | references/actions.md |
GitHub Actions (workflows + runs) |
| ci / monitor ci / check ci / ci status / watch ci | references/ci-monitor.md |
monitor CI checks with live polling (if user says bare "ci", ask: monitor checks or view workflows?) |
| pr dashboard / pr overview / open prs / my prs / pr status | references/pr-dashboard.md |
PR overview with status classification |
| release / publish release | references/release.md |
releases + assets + verification |
| release strategy / release format / versioning | references/release-strategy.md |
versioning, title/description format, generation protocol |
| secrets / variables | references/secrets-vars.md |
manage secrets and variables |
| project | references/projects.md |
projects operations |
| gist | references/gists.md |
gist operations |
| search | references/search.md |
search repos/issues/prs/code |
| api | references/api.md |
gh api (advanced) |
| extension | references/extensions.md |
manage gh extensions |
| config | references/config.md |
gh config basics |
Safety Rules
- Confirm before any state-changing operation (create/edit/delete/merge/close).
- Never upload secrets as assets.
- Treat
gh apias powerful: confirm before any write operation. - Never delete or move published releases/tags unless explicitly requested.
- When creating PRs, always set an assignee: default to
@meunless the user explicitly names someone else. - When creating PRs, apply relevant existing labels when possible; auto-pick from PR context (title/body/branch + changed paths) and avoid creating new labels unless truly necessary.
- If labels must be created, retrieve existing labels first (
gh label list), propose the minimal set consistent with repo naming, and confirm beforegh label create.
What ships with it
21 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.
- README.md 1.1 KB
- references/actions.md 447 B
- references/api.md 313 B
- references/auth.md 623 B
- references/ci-monitor.md 4.0 KB
- references/cli-help.md 329 B
- references/config.md 165 B
- references/extensions.md 245 B
- references/gists.md 157 B
- references/issue.md 343 B
- references/pr-dashboard.md 4.4 KB
- references/pr.md 1.9 KB
- references/projects.md 190 B
- references/release-assets.md 879 B
- references/release-create.md 1.9 KB
- references/release-manage.md 925 B
- references/release-strategy.md 7.5 KB
- references/release.md 705 B
- references/repo.md 355 B
- references/search.md 230 B
- references/secrets-vars.md 388 B
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 · 79 lines · 131 tokens per session scan A 56daef387084
github is a skill published in the GitHub repository bntvllnt/agent-skills (17 stars, last pushed 4mo ago), licensed MIT. It adds 131 tokens to every session and 907 once invoked, about $0.0005 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
codex-issue-coordinator
Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
github
GitHub CLI operations via gh for issues, PRs, Actions, releases, and REST/GraphQL API with --json/--jq parsing. Triggers on: "create an issue", "submit a PR", "check CI status", "why did CI fail", "merge a PR", or pasted GitHub URLs.
release
Verify, write the CHANGELOG, cut a version — then hand the release sequence back.
mlops-collaboration
Prepare a project for public collaboration — license, code of conduct, docs, branch rulesets, templates, and git-cliff releases. Use when open-sourcing a repository, onboarding contributors, or cutting a tagged release.
git-workflow
Branching strategies, conventional commits, PR templates, and merge vs rebase guidance. Activate when starting features, creating PRs, or managing releases.