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/abilityai/abilities/commitnpx skills add Abilityai/abilities --skill commitgit clone --depth 1 https://github.com/Abilityai/abilitiesWhat 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 | $0.00023 | $0.00953 |
| Opus 5 | $0.00012 | $0.00477 |
| Sonnet 5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
commit 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.commit vX.Y — recent: <summary>. Then proceed.
Stage changed skill files, write a commit message tied to the in-progress issue, and close the issue with a summary. The single action that closes the loop between a GitHub issue and a SKILL.md change.
State Dependencies
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| GitHub Issues | Current repo | Yes | Yes | Close the in-progress issue |
| Git working tree | ./ | Yes | Yes | Stage and commit skill files |
Prerequisites
ghCLI authenticated- Git repo with at least one commit (not bare)
- Work is in-progress (a claimed issue exists)
Process
Step 1: Find the In-Progress Issue
gh issue list --label "status:in-progress" --state open --json number,title,body,labels --limit 5
If an issue number was passed as $ARGUMENTS, use that instead.
If multiple in-progress issues, ask which one this commit closes.
Step 2: Check for Changes
git status --short
Surface all modified, added, or deleted files. Flag anything that is NOT a SKILL.md or agent configuration file (CLAUDE.md, template.yaml) — confirm the user wants to include it.
If there are no changes at all: report "Nothing to commit. Did /adjust-playbook or /create-playbook run yet?"
Step 3: Stage Files
Stage all changed agent files:
git add .claude/skills/
git add CLAUDE.md # if modified
If other files were modified, confirm before staging.
Show the staged diff summary:
git diff --cached --stat
Step 4: Compose Commit Message
Derive the commit message from the issue:
- If the issue has a
skill:*label:[$SKILL_NAME]: $SHORT_DESCRIPTION (closes #$NUMBER) - If project-level:
[agent]: $SHORT_DESCRIPTION (closes #$NUMBER) - Short description = condensed version of issue title (lowercase, imperative)
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 · 144 lines · 23 tokens per session scan A 26c2e98ce5cc
commit is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 23 tokens to every session and 953 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
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…