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 agentmods add skills/yc-software/qm/github-gitlabnpx skills add yc-software/qm --skill github-gitlabgit clone --depth 1 https://github.com/yc-software/qmWhat 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 | $0.00025 | $0.00775 |
| Opus 5 | $0.00013 | $0.00387 |
| Sonnet 5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
github-gitlab 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub / GitLab
Use this skill when the user asks to inspect repos, issues, pull requests, merge requests, code history, branches, or to make a small code change in a hosted repo.
This is a resident-machine-auth connector. Prefer the native CLIs (gh, glab) and
git, using the agent computer's logged-in state. Do not ask the user to paste tokens,
and do not rely on proxy bearer-token injection.
One exception: if the system prompt lists a shared org credential for a Git remote, the
token is broker-only and never appears on the computer. For clone/fetch/push, use the
core-hosted smart HTTP remote documented in skills/use-shared-credential/SKILL.md.
That keeps normal git workflows working while core injects the upstream credential
server-side.
Logging in
If gh auth status (or glab auth status) fails, log in with the native command:
gh auth login
The platform recognizes this device-flow login and runs it as a durable process
session (ADR 0002): it prints the one-time code + verification URL immediately and keeps
polling on the agent computer across turns — it does not block your turn or die at
teardown. Give the user the code and URL, ask them to approve in the browser, then say
"done". On the next turn, run gh auth status (or gh auth login again): the platform
reports you're authenticated once approval completes, and the login self-expires if the
user takes too long (just run gh auth login again to restart). GitLab is the same with
glab auth login.
Read-only work
Check auth and inspect repo state:
gh auth status
gh repo view OWNER/REPO --json name,description,url,defaultBranchRef
gh issue list --repo OWNER/REPO --state open --limit 20
gh pr list --repo OWNER/REPO --state open --limit 20
For GitLab:
glab auth status
glab repo view GROUP/PROJECT
glab issue list --repo GROUP/PROJECT
glab mr list --repo GROUP/PROJECT
Use git log, git show, and git diff for codebase-change summaries. Cite commit
hashes, PR/MR numbers, and links.
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.
- 2d ago First seen · 99 lines · 25 tokens per session scan A 17de274d57f8
github-gitlab is a skill published in the GitHub repository yc-software/qm (14,360 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 775 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.
Other skills, from other repositories
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
adding-a-provider-api-feature
Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
openclaw-ci-limits
Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe ramp-down/ramp-up changes. Use when tuning .github/workflows/, docs/ci.md, CI runner labels, matrix max-parallel…
release-openclaw-plugin-testing
Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.