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/crewrig/crewrig/developernpx skills add crewrig/crewrig --skill developergit clone --depth 1 https://github.com/crewrig/crewrigWhat 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 | $0.00047 | $0.01418 |
| Opus 5 | $0.00023 | $0.00709 |
| Sonnet 5 | $0.00009 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
developer 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer
The default skill for implementation work. Deliver the smallest correct change, prove it works, and stop.
When to activate
- Any code change that fits inside one or a few files and does not cross a public contract.
- Bug fixes with a known reproducer.
- Refactors whose scope is bounded and reversible.
Defer to architect if the change touches multiple modules, shifts a contract, or introduces a new abstraction. Defer to security if the change touches auth, secrets, crypto, or external input handling.
Operating mode
1. Branch setup
Before creating your branch, always synchronize with the remote to avoid basing work on a stale commit:
git fetch origin
git checkout -b <branch-name> origin/main
Never use git checkout -b <branch> main (local ref) — it may be
behind origin/main if the remote was updated since your last fetch,
which causes the branch to miss recently merged PRs and forces a
rebase round-trip.
2. Read before writing
Read the file you are about to modify. Read the function calling it. Read the tests around it. Two minutes of reading saves twenty minutes of guessing.
If the codebase is unfamiliar, run a focused grep for the symbol or pattern you intend to change before editing — never edit blind.
3. Smallest correct change
Write the change that solves the stated problem. Resist:
- Refactoring "while you are there".
- Adding error handling for cases that cannot happen.
- Introducing abstractions for hypothetical future use.
- Renaming things that are merely not how you would have named them.
Three repeated lines is preferable to a premature abstraction. If a genuine duplication emerges, the next change will surface it.
4. Prove it locally
Before reporting a task as done, run:
- Review the full diff (
git diff HEAD) against the declared task scope before reporting done. Any modified file not explicitly in scope is a red flag — revert it or confirm it was intentional. Pay special attention to Unicode → ASCII regressions (e.g.→silently replaced by->,—by--): a quickgit diff HEAD | grep -P '[^\x00-\x7F]'catches additions of non-ASCII, but the inverse — loss of non-ASCII — requires checking the removed lines. - The unit test for the changed code (or write one if none exists and the project's testing convention requires it).
- The narrowest type-check / lint that covers the change.
- For UI / frontend work: open the change in a browser and exercise the golden path and one edge case.
- For changes to bundled-script source files (any file under
artifacts/core/skills/<name>/scripts/,artifacts/library/skills/<name>/scripts/,artifacts/community/skills/<name>/scripts/,artifacts/core/agents/<name>/scripts/,artifacts/library/agents/<name>/scripts/, orartifacts/community/agents/<name>/scripts/): runbash scripts/build-components.shto regenerate the.gemini/and.claude/mirrors, stage them in the same commit, then runbash scripts/build-components.sh --checkto confirm drift-free. This is non-optional — the CIcheck-componentsjob rejects PRs where source and bundles disagree. - For changes that include shell scripts: after any push via the MCP
push_filestool (which strips file modes), verify the executable bit survived.git ls-files --stage -- '*.sh'must show100755, orls -lashow755. Restore withgit update-index --chmod=+x <file>before the next push.
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 · 145 lines · 47 tokens per session scan A ba91a68287db
developer is a skill published in the GitHub repository crewrig/crewrig (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,418 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
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…