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/aretw0/agents-lab/githubnpx skills add aretw0/agents-lab --skill githubgit clone --depth 1 https://github.com/aretw0/agents-labWhat 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 | $0.00030 | $0.00761 |
| Opus 5 | $0.00015 | $0.00380 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
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 yesterday.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Skill
Use the gh CLI to interact with GitHub. Always specify --repo owner/repo when not inside a git directory, or pass URLs directly.
Disable interactive prompts in agent-run commands:
GH_PROMPT_DISABLED=1 gh <command>
Board-first issue mirroring
When this workspace uses .project/tasks.json as the canonical board, treat GitHub Issues as an external mirror unless the operator explicitly says otherwise.
Mapping:
- GitHub issue
number/URL -> task note/evidence external reference. - GitHub issue title -> task description summary, preserving local task id as canonical id.
- GitHub labels -> task priority/milestone only through an explicit mapping recorded in the task notes.
- GitHub state closed/open -> mirror of local status, not an auto-close authority.
Sync policy:
- Prefer
.project-> GitHub for publication/mirror updates. - Never close local tasks solely because a GitHub issue is closed; require local verification evidence.
- On conflict, append an audit note and ask for/rely on the board policy rather than overwriting silently.
- Do not mutate public GitHub metadata or issue state without explicit operator intent.
Issues
# List open issues
gh issue list --repo owner/repo
# View an issue
gh issue view 42 --repo owner/repo
# Create an issue
GH_PROMPT_DISABLED=1 gh issue create --title "..." --body "..." --repo owner/repo
# Close an issue
gh issue close 42 --repo owner/repo
Pull Requests
# List PRs
gh pr list --repo owner/repo
# View a PR
gh pr view 55 --repo owner/repo
# Create a PR (always provide title and body — never rely on interactive editor)
GH_PROMPT_DISABLED=1 gh pr create --title "..." --body "..." --repo owner/repo
# Check CI status on a PR
gh pr checks 55 --repo owner/repo
# Merge a PR
GH_PROMPT_DISABLED=1 gh pr merge 55 --squash --delete-branch --repo owner/repo
CI / Workflow Runs
# List recent runs
gh run list --repo owner/repo --limit 10
# View a specific run
gh run view <run-id> --repo owner/repo
# View only failed step logs
gh run view <run-id> --repo owner/repo --log-failed
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.
- yesterday First seen · 105 lines · 30 tokens per session scan A 075a23e97d76
github is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 761 once invoked, about $0.0002 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
agentbro-release
Use when releasing AgentBro from this repository: merging dev/main, bumping versions, updating release notes, tagging, pushing, monitoring GitHub Actions, Homebrew cask publication, or fixing a bad release.
agentbro-pr-merge
Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.
source-command-check
跑全套本地校验(前端 lint/test/build + Rust check)。.
gpt-control
Use when the user asks to get an independent ChatGPT web review, continue a GPT-Control conversation, inspect a model run, or generate or iterate on an image through a configured browser driver. Not for facts the working tree or a local test can answer directly.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.