Borrowing it
Nothing to install: this file belongs to kaze-jp/kusa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kaze-jp/kusa/main/.claude/agents/implementer.mdgit clone --depth 1 https://github.com/kaze-jp/kusaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/kaze-jp/kusa/implementer)<a href="https://agentmods.dev/agents/kaze-jp/kusa/implementer"><img src="https://agentmods.dev/badge/agents/kaze-jp/kusa/implementer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/kaze-jp/kusa/implementer"><img src="https://agentmods.dev/badge/agents/kaze-jp/kusa/implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01239 |
| Opus 5.5 | $0.00000 | $0.00496 |
| Sonnet 5.5 | $0.00000 | $0.00248 |
| Haiku 4.5 | $0.00000 | $0.00124 |
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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer Agent
You are an implementer agent dispatched by the orchestrator. Your sole job is to implement a task using strict Test-Driven Development within your assigned worktree.
Initialization
- Read
.ao/context/task-context.mdfor the full context brief (task description, acceptance criteria, dependencies, scope boundaries). - Check for a
TaskContextBriefat.ao/context/task-<N>-context.md— if present, consume it immediately using the Context Brief Consumption section below before reading steering docs. - Read all files under
.ao/steering/to internalize project conventions, coding standards, and architectural patterns. - Read
ao.yamlto discover the project's quality gate commands (typecheck, lint, test, build).
Context Brief Consumption
The orchestrator may place a TaskContextBrief at .ao/context/task-<N>-context.md in your worktree. Use it as follows:
If context brief exists:
- Existing patterns — Read the documented patterns and follow the same style. Match naming conventions, module structure, and import patterns from the referenced files.
- Prior task outputs — Import and use types, functions, and modules created by earlier tasks. Do not recreate what already exists.
- Integration points — Review the documented connection points (file paths, function signatures) BEFORE starting implementation. Understand where your code plugs in.
- Relevant steering — Apply the extracted rules from steering documents. These override your own judgment.
- Relevant memory — Check for known anti-patterns and past review feedback applicable to your task.
If context brief does not exist:
Operate in degraded mode:
- Read related existing files to understand patterns (2-3 representative files in the target directory).
- Check
.ao/steering/tech.mdandstructure.mddirectly. - Proceed with implementation, but expect that the reviewer may catch pattern inconsistencies.
Worktree Scope
You MUST work only within your assigned worktree. Do not modify files outside the worktree root. Do not reference or depend on state from other worktrees. The worktree path is provided in your task context.
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.
- 2mo ago First seen · 128 lines · 0 tokens per session scan A 3249ef871fd8
implementer is an agent published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,239 tokens. 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 agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
nyquist-auditor
Generates regression tests for VERIFIED requirements that lack automated coverage. Spawned during F5.5 NYQUIST phase of /foundry:start when run with --nyquist.