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/clawnify/greybeard/skillifynpx skills add clawnify/greybeard --skill skillifygit clone --depth 1 https://github.com/clawnify/greybeardWhat 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 | $0.00046 | $0.00741 |
| Opus 5 | $0.00023 | $0.00370 |
| Sonnet 5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
skillify 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillify
Capture the work you just did as a reusable, parameterized skill — then register it in the resolver so it can be found and reused. This is the move that compounds a one-off into a capability.
"You just do anything, and then I like it, I say skillify it — and it becomes basically like a tool call or a method call. And the most important part is plugging it into the resolver." — Pete Koomen / Andrej Karpathy, YC
When to run
- The user says "skillify this" / "make this a skill" / "save this as a skill".
- You just completed a multi-step procedure that you (or a teammate) will plausibly do again.
Do not skillify trivial one-liners or anything a single existing tool already does.
Procedure
-
Identify the procedure. Look at what was just done in this session — the steps, the order, the decisions, the gotchas. Strip out the one-off specifics (this particular file, this particular value).
-
Generalize into parameters. Anything that changed between "this run" and "the next run" becomes an input, not a hardcoded value. A good skill is the shape of the work, not a replay of one instance.
-
Check before you write — DRY. Read the resolver (see "The resolver" below) and skim existing skills. If one already covers this, extend it with a parameter instead of adding a near-duplicate. Adding skill #2 that overlaps skill #1 makes the library worse, not better.
-
Write the skill. Create
skills/<kebab-name>/SKILL.mdwith frontmatter and a tight procedure:--- name: <kebab-name> description: <what it does> + Use when <the trigger>. --- # <Title> ## Inputs - `<param>` — <what it is> ## Procedure 1. ... 2. ...Keep it minimal. The procedure should read like the steps a careful teammate would follow — no speculative options, no abstractions for a single use.
-
Register it in the resolver. Add one line to the index the agent actually reads:
name+ a one-line use-when + a link toskills/<kebab-name>/SKILL.md. A skill that isn't in the resolver doesn't exist.
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 · 58 lines · 46 tokens per session scan A cfb2819d7fc0
skillify is a skill published in the GitHub repository clawnify/greybeard (6 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 741 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 2026-08-31.
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…