worker-research

A codebase research workflow for tracing how a real feature or request moves through a repository.

In plain words
What is it for?
Use it to locate symbols, endpoints, configuration, callers, owners, and the shortest verified route for a bounded bug fix or architecture question.
Why use it?
It helps avoid searching the whole codebase and reduces guesses about where a problem or responsibility actually belongs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/megamen32/lasthumancommit/worker-research
Any agent
npx skills add megamen32/LastHumanCommit --skill worker-research
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit

Made for: Claude Code, Codex.

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00106 $0.01278
Opus 5 $0.00053 $0.00639
Sonnet 5 $0.00021 $0.00256
Haiku 4.5 $0.00011 $0.00128

Measured 2d ago against content hash 9a10d76afd3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

worker-research 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/code_map.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/last-human-commit/skills/worker-research/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worker Research

Find the shortest verified route to the next business proof. Do not map the whole repository.

Tool order

  1. Search existing reusable knowledge before rediscovering it:

    python3 <this-skill-directory>/scripts/code_map.py \
      --root "$PWD" search <business-noun> <symbol>
    

    Resolve scripts/code_map.py from this skill directory. Treat every hit as a lead: run check, then confirm the decisive location with one targeted rg or source read.

  2. Use rg --files, then rg -n -C as the default fresh search. Trace from the real consumer inward. Search exact endpoint names, commands, config keys, symbols, and user-visible strings before broad concepts.

  3. Use context-mode for large files, logs, test output, or three or more related searches. Ask it focused questions and return only derived evidence. It is a context-saving processor and index, not the durable source of truth.

  4. Use an existing Graphify graph when the decision depends on three or more components, indirect callers, ownership, or cross-language flow. Verify every decisive graph edge against current source with rg. Do not build or refresh a graph for a simple symbol lookup.

  5. Stop when Lead has the production path, owning locations, first blocker, cheapest patch route, proof, and decision-relevant unknowns.

In practice: rg is the fastest and most authoritative locator; Graphify is useful orientation for multi-hop structure but can be stale or over-broad; context-mode is highly effective for preserving context on large output but does not by itself prevent future rediscovery.

Bugfix route

For a defect, preserve this order in the research receipt: telemetry -> reproduction -> smallest failing test -> root cause -> patch -> regression.

  1. Use telemetry to locate the failing boundary; do not infer the fix from a stack trace, alert, or log alone.
  2. Reproduce the same failure through the real consumer path with the smallest deterministic probe available.
  3. Add or specify the smallest failing test that proves the accepted behavior, not an implementation detail.
  4. Patch only the verified root cause when mutation is authorized.
  5. Re-run the failing proof, proportional regression checks, and the cheapest claim-matching business canary.

Read the full file on GitHub · 118 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 2d ago First seen · 118 lines · 106 tokens per session scan A 9a10d76afd3d

Subscribe to this mod's changes

worker-research is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 1,278 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens