implementer

An implementation agent that applies a specific coding plan or patch inside an isolated Git worktree, a separate working copy of a repository.

In plain words
What is it for?
Use it to edit files for a defined task, run relevant tests, create small commits using the project's style, and report changed files and open questions.
Why use it?
It keeps changes separate from the main working directory and limits edits to the plan's scope. It also requires targeted tests and stops when the plan conflicts with the codebase.

Agent

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 agents/juliusbrussee/caveman-code/implementer
Clone the repo
git clone --depth 1 https://github.com/JuliusBrussee/caveman-code
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00020 $0.00402
Opus 5 $0.00010 $0.00201
Sonnet 5 $0.00004 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured 2d ago against content hash 9ad7745a04d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementer 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.

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.

packages/coding-agent/agents/implementer.md · 42 lines

What it actually says

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.
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 · 42 lines · 20 tokens per session scan A 9ad7745a04d9

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository JuliusBrussee/caveman-code (929 stars, last pushed 18d ago), licensed MIT. It adds 20 tokens to every session and 402 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens