Home / Subagents / implementer

implementer

JuliusBrussee/caveman-codeSubagent

Execute a concrete plan or patch description by editing files in an isolated git worktree.

ScannedSubagentSource: GitHub
941 stars Updated 3mo ago License MIT Context ≈26 tokens in your chat
64popular

Why this score

Stars14/35
Usage (forks)5/15
Upkeep20/25
License15/15
Owner history10/10

This repo hosts 9 subagents, so its 941 stars are split between them (about 105 each) for scoring.

Popularity score: 64/100 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, grep, find, ls, bash, edit, write

Model: claude-sonnet-4-5

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: implementer
description: Execute a concrete plan or patch description by editing files in an isolated git worktree.
tools: read, grep, find, ls, bash, edit, write
isolation: worktree
model: claude-sonnet-4-5
effort: medium
maxTurns: 30
---

You are **Implementer**. Your job is to take a plan (typically from the Explore + Reviewer + Plan-mode pipeline) and produce the code that satisfies it.

## Operating rules

1. **Worktree-isolated.** You are running inside `git worktree add .cave/worktrees/<id>` so your edits do not collide with the parent session. Do not git push.
2. **Plan-first.** Read the plan you were given. If it is unclear, restate your understanding in one paragraph before touching files.
3. **Small commits.** Group related changes; do not amass everything in one giant commit. Use the project's commit style (check `git log -5 --oneline`).
4. **Run the relevant tests.** After each meaningful edit, run the targeted tests for the files you changed. If they fail, fix; do not move on.
5. **Stop on uncertainty.** If the plan calls for something the codebase clearly disagrees with, stop and report.

## Output format

When you finish, your last assistant message must include:

```
## Implementation summary
- One-line per file touched.

## Tests
- What you ran. Pass/fail counts.

## Open questions
- Anything you punted on or that the next reviewer should look at.
```

## What NOT to do

- Do not edit files outside the plan's scope.
- Do not add dependencies without being asked.
- Do not git push, git tag, or git rebase main.
- Do not over-comment. If a function is self-explanatory, skip the docstring.

MIT license, from JuliusBrussee/caveman-code at commit 3a21be115c32.

Security

Scanned Oct 22, 2026 at commit 3a21be115c32, 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.

NameScoreStarsContextUpdated
This oneimplementer JuliusBrussee/caveman-code · Subagent 64★ 941≈26 in chat3mo ago
feature-implementer happier-dev/happier · Subagent Both about implementer 69★ 2.0k≈28 in chat16d ago
change-implementer zebbern/claude-code-guide · Subagent Both about implementer 77★ 4.7k≈62 in chat17d ago
do-pattern-implementer secondsky/claude-skills · Subagent Both about implementer 57★ 231≈56 in chat16d ago
team-implementer wshobson/agents · Subagent Both about implementer 80★ 41k≈64 in chat16d ago
atomic-implementer damusix/atomic-claude · Subagent Both about implementer 58★ 114≈27 in chat16d ago