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/clonenpx skills add Abilityai/abilities --skill clonegit 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 | $0.00021 | $0.00691 |
| Opus 5 | $0.00010 | $0.00345 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
clone-cornelius scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clone Cornelius
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.clone-cornelius vX.Y — recent: <summary>. Then proceed.
Clone Cornelius and launch Claude Code inside the repository.
STEP 1: Determine Destination
If the user provided a destination path as an argument, use it. Otherwise, ask:
Use AskUserQuestion:
- Question: "Where should Cornelius be cloned?"
- Header: "Installation Location"
- Show these options:
~/cornelius— Home directory (recommended)./cornelius— Current directory- Custom path — Let me specify
Default to ~/cornelius if no preference.
Expand ~ to the actual home directory using:
echo "$HOME"
STEP 2: Clone the Repository
git clone https://github.com/Abilityai/cornelius [destination]
If the destination already exists and is non-empty, inform the user and stop — do not overwrite.
Report the result:
## Cornelius Cloned
Repository cloned to: [full path]
STEP 3: Instruct the User to Open Claude Code Inside Cornelius
Display this message to the user:
## Next Step: Open Claude Code in Cornelius
Cornelius is a Claude Code agent — to use it, you need to start Claude Code
with the Cornelius directory as its working directory.
**Option 1 — Exit and reopen (recommended)**
Exit this Claude Code session, then run:
cd [destination]
claude
**Option 2 — Open a new terminal tab**
Keep this session open and run in a new terminal tab:
cd [destination]
claude
**Option 3 — Use the shell command directly**
claude [destination]
Once Claude Code starts inside Cornelius, it will load the agent's CLAUDE.md
and you'll be working with Cornelius.
Do not do anything else. The skill is complete once the instructions are displayed.
Error Handling
| Situation | Action |
|---|---|
git not found |
Tell user to install Git first: brew install git or https://git-scm.com |
| Destination already exists | Warn the user, offer to use existing clone or pick a different path |
| Clone fails (network, permissions) | Show the error and suggest they try manually: git clone https://github.com/Abilityai/cornelius |
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 · 101 lines · 21 tokens per session scan A a56671323ca7
clone-cornelius is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 21 tokens to every session and 691 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…