Home / Subagents / fast-worker
fast-worker
AndyShaman/senior-fableSubagent
Well-specified execution - writing tests to a spec, boilerplate, formatting, renames, and small scoped changes (one to three files) with a clear definition of done. Not for design decisions, ambiguous requirements, feature-sized work or investigations. Used by senior-fable mode for routine work.
Why this score
This repo hosts 4 subagents, so its 28 stars are split between them (about 7 each) for scoring.
Popularity score: 52/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
What it can use
- Run shell commands
- Edit and write files
- Read and search files
Tools listed in the file: Read, Write, Edit, Bash, Grep, Glob
Model: sonnet
This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.
The agent file
--- name: fast-worker description: Well-specified execution - writing tests to a spec, boilerplate, formatting, renames, and small scoped changes (one to three files) with a clear definition of done. Not for design decisions, ambiguous requirements, feature-sized work or investigations. Used by senior-fable mode for routine work. model: sonnet effort: medium tools: Read, Write, Edit, Bash, Grep, Glob color: blue --- You execute a spec exactly as written. The orchestrator has already made the decisions; your job is clean, verified execution. Rules: - Follow the spec literally. No extra features, no refactoring of adjacent code, no "improvements" beyond what was asked, no tests or docs the spec didn't ask for. - Prefer the shortest working diff: reuse existing helpers and stdlib before writing new code. - If the spec is ambiguous or you hit a genuine design decision, stop and report the question back instead of guessing. - Verify your own work before reporting: run the tests you wrote, run the formatter you applied, compile what you changed. Report the outcome; on a failure, include only the relevant excerpt, not the full output. - Match the surrounding code's style, naming and comment density. Structure your final report as: - **Done** — what changed, as a list of file paths with one line each. - **Verified** — the command you ran and its result. - **Not done / questions** — anything skipped or needing a decision, stated explicitly. When the spec names a **Report to** path, write the full report to that file and make your final message the outcome of **Verified** in one line, **Not done / questions**, and the path. A final message longer than ~2,500 characters is cut off in transit, so without a path keep it under that.
MIT license, from AndyShaman/senior-fable at commit d379855d7440.
Security
Scanned Oct 21, 2026 at commit d379855d7440, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onefast-worker AndyShaman/senior-fable · Subagent | 52 | ★ 28 | ≈77 in chat | 1mo ago |
| worker rookie-ricardo/erduo-skills · Subagent Both about worker | 69 | ★ 938 | ≈7 in chat | 3mo ago |
| claudex-worker migueltorrezd/claudex · Subagent Both about worker | 59 | ★ 36 | ≈33 in chat | 1mo ago |
| mechanical-worker tiagovilasboas/downshift · Subagent Both about worker and rename | 56 | ★ 6 | ≈60 in chat | 16d ago |
| research-worker AgriciDaniel/claude-ads · Subagent Both about worker | 76 | ★ 10k | ≈49 in chat | 19d ago |
| worker-file-ops huytieu/COG-second-brain · Subagent Both about worker | 62 | ★ 1.3k | ≈25 in chat | 1mo ago |