Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultnpx agentmods add skills/georgekhananaev/claude-skills-vault/github-cliWrote 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/georgekhananaev/claude-skills-vault/github-cli)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/github-cli"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/github-cli/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/georgekhananaev/claude-skills-vault/github-cli"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/github-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00055 | $0.02871 |
| Opus 5 | $0.00028 | $0.01435 |
| Sonnet 5 | $0.00011 | $0.00574 |
| Haiku 4.5 | $0.00006 | $0.00287 |
Grade A, and why
github-cli 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 6d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI
Safety-first wrapper for GitHub CLI (gh). Every command is classified by risk level before execution.
When to Use
- User asks to create, list, merge, or close PRs
- User asks to manage issues, releases, or repos
- User asks to check CI/CD status or workflow runs
- User asks to call the GitHub API via
gh api - User asks to manage GitHub Actions secrets or variables
Prerequisites
- Install:
brew install ghor see https://cli.github.com - Auth:
gh auth login - Verify:
gh --version(requires v2.86+) - Scopes:
gh auth status— confirmrepo,read:orgscopes minimum
Safety Model
Every gh command falls into one of four risk tiers:
| Tier | Action Required | Examples |
|---|---|---|
| Safe | Execute immediately | gh pr list, gh issue view, gh repo view |
| Write | Inform user, then execute | gh pr create, gh issue create, gh release create |
| Destructive | AskUserQuestion BEFORE executing |
gh pr merge, gh pr close, gh release delete |
| Forbidden | Multi-step validation, NEVER auto-confirm | gh repo delete, gh repo transfer, visibility changes |
See references/safety-rules.md for the full classification and confirmation templates.
Decision Flow
Command received
→ Classify risk tier (see Quick Reference)
→ Safe? Execute immediately
→ Write? Inform user what will happen → execute
→ Destructive? AskUserQuestion with options → wait for answer → execute or cancel
→ Forbidden? Warn → require typed confirmation → final confirm → execute or cancel
Quick Reference
Safe (read-only, execute immediately)
| Command | Description |
|---|---|
gh pr list |
List pull requests |
gh pr view |
View PR details |
gh pr checks |
View CI status |
gh pr diff |
View PR diff |
gh issue list |
List issues |
gh issue view |
View issue details |
gh repo view |
View repo info |
gh repo list |
List repos |
gh repo clone |
Clone a repo |
gh release list |
List releases |
gh release view |
View release details |
gh run list |
List workflow runs |
gh agent-task list / view |
List/inspect Copilot coding-agent tasks (v2.80+) |
gh run view |
View run details |
gh run view --log |
View run logs |
gh workflow list |
List workflows |
gh workflow view |
View workflow details |
gh run download |
Download workflow artifacts |
gh api (GET) |
Read-only API calls |
gh auth status |
Check auth |
gh browse |
Open repo in browser |
gh status |
Check your GitHub dashboard |
gh gist list |
List your gists |
gh gist view |
View gist details |
gh label list |
List labels |
gh search repos |
Search repos |
gh search issues |
Search issues |
gh search prs |
Search PRs |
gh search code |
Search code |
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.
- 6d ago First seen · 351 lines · 55 tokens per session scan A 9f66e5e5a831
github-cli is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 29d ago), licensed MIT. It adds 55 tokens to every session and 2,871 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
release-skills
A release workflow for preparing and publishing a new version of a software project. A release is a named version that may include updated version files, release notes, tags, or a GitHub Release.
version-release
Choose and apply the correct semantic version bump for this repository. Use for every user-visible release, before merge when a change set should ship as patch, minor, or major, and whenever package/plugin/desktop version metadata must stay synchronized.
changelog-gen
A changelog generator that turns Git history into a version-by-version record of project changes. A changelog is a readable summary of new features, fixes, breaking changes, documentation, and other updates.
create-release-checklist
Create a release checklist and GitHub issue for an R package. Use when the user asks to "create a release checklist" or "start a release" for an R package.
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers: unpublished changes, changelog, what changed, whats new.