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/megamen32/lasthumancommit/worker-codenpx skills add megamen32/LastHumanCommit --skill worker-codegit clone --depth 1 https://github.com/megamen32/LastHumanCommitWhat 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 | $0.00083 | $0.00490 |
| Opus 5 | $0.00042 | $0.00245 |
| Sonnet 5 | $0.00017 | $0.00098 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
worker-code 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.
What it actually says
Worker Code
Implement one accepted business vertical. Lead owns route and integration.
Procedure
- Confirm the accepted outcome, actual consumer, allowed paths, exclusions, and cheapest sufficient proof.
- Search the reusable code map with the sibling Worker Research tool, then
verify relevant locations with targeted
rg. Do not repeat broad research already captured as fresh verified knowledge. - Trace the production call chain before editing an adjacent adapter, fixture, abstraction, or test double.
- Reuse the existing mechanism and implement the thinnest usable vertical.
- Run the real or closest claim-matching canary early. Fix only the first claim-blocking failure and add proportional direct-regression evidence.
- If the patch changes a durable production path, owner, or config location,
resolve
../worker-research/scripts/code_map.pyfrom this skill and upsert the affected key. Do not record ordinary task progress. - Stop when the assigned claim is proven.
Lead interaction
Ask Lead whenever its broader user context can change behavior, product choice, scope, proof strength, ownership, or a consequential action. Send concise evidence, recommendation/default, parallel-safe work, and the exact blocked action through a non-blocking parent transport; continue edits valid under every plausible answer.
At each 20-minute checkpoint report measured timing, changed files, business delta, blocker, whether the route remains shortest, and the smallest next action. The checkpoint redirects work; it does not kill the Worker.
Do not
- Do not implement horizontal completeness before the first usable path.
- Do not redesign, refactor, harden, document, or add compatibility work unless the current business claim requires it.
- Do not treat compilation or unit tests as user-facing proof.
- Do not trust a graph, context index, code map, or old task card over current source and the latest user outcome.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 47 lines · 83 tokens per session scan A 016b1c2bc793
worker-code is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 490 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…