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/duyet/oma/githubnpx skills add duyet/oma --skill githubgit clone --depth 1 https://github.com/duyet/omaWhat 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 | $0.00081 | $0.00915 |
| Opus 5 | $0.00041 | $0.00458 |
| Sonnet 5 | $0.00016 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
github scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
github
The sandbox ships the gh CLI. Prefer gh over raw git push to GitHub's web
API — it's authenticated, scriptable, and JSON-friendly (--json + --jq).
Auth assumptions
- Auth is provided by the platform (a
cap_clicredential injected at the network layer, orGH_TOKEN/GITHUB_TOKENin the environment). Do not ask the user to paste a token, and don't rungh auth logininteractively. - Verify once:
gh auth status. If it fails, report that the repo needs a GitHub credential attached (aghcap_clicredential orGH_TOKEN) — don't try to work around missing auth.
Issues
gh issue list --state open --limit 20 --json number,title,labels
gh issue view 42 --comments
gh issue create --title "…" --body "…" --label bug # never invent labels that don't exist
gh issue comment 42 --body "…"
gh issue close 42 --comment "fixed in #57"
Pull requests
# create from the current branch (never from the default branch — branch first)
gh pr create --title "feat(x): …" --body "$(cat <<'EOF'
## What
## Why
## Testing
EOF
)" --base main
gh pr list --json number,title,headRefName,statusCheckRollup
gh pr view 57 --json title,body,reviewDecision,mergeStateStatus
gh pr diff 57
Rules:
- Branch before you commit. If you're on the default branch (
main/master), create a feature branch first — never push commits straight to the default branch. - Write a real PR body: what changed, why, how it was tested. No empty descriptions.
- Never
--force/--force-with-leasepush unless the user explicitly asks and understands the branch will be rewritten. Rewriting shared history is destructive.
Reviews
gh pr review 57 --comment --body "…" # leave feedback without a verdict
gh pr review 57 --approve --body "LGTM"
gh pr review 57 --request-changes --body "…"
When reviewing, read the diff (gh pr diff), check the PR description matches
the change, and look at CI before approving.
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 · 93 lines · 81 tokens per session scan A 56023f6cb47a
github is a skill published in the GitHub repository duyet/oma (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 81 tokens to every session and 915 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…