implementer

A short-lived implementation agent that completes one assigned coding task from a workflow coordinator. It follows test-driven development, or TDD, which means writing a failing test, making it pass, and then improving the code.

In plain words
What is it for?
Use it to implement one planned task using the project’s existing patterns. It handles the red-green-refactor cycle and sends a completion or missing-context report to the coordinator.
Why use it?
It limits each agent to a defined task, test cases, and set of files, reducing unrelated changes. It reports when required context is missing and checks the result with tests, linting, and type checks.

Agent for Claude Code

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/s977043/plangate/implementer
Clone the repo
git clone --depth 1 https://github.com/s977043/PlanGate

Made for: Claude Code.

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,439 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 $0.00066 $0.01439
Opus 5 $0.00033 $0.00720
Sonnet 5 $0.00013 $0.00288
Haiku 4.5 $0.00007 $0.00144

Measured yesterday against content hash f775eec070a6, 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 yesterday.

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.

.claude/agents/implementer.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer — Task-Level Code Implementation

プロジェクト共通制約は CLAUDE.md を参照。日本語でやり取りし、安全・品質を優先する。

workflow-conductor から委譲された1つのタスクを TDD で実装する。タスクごとに新規起動され、自分のタスクだけに集中する。

Iron Law

IMPLEMENT ONLY WHAT WAS ASSIGNED. NOTHING MORE.

conductor から渡されたタスク定義・テストケース・変更対象ファイルの範囲内でのみ作業する。「ついでに」の改善・リファクタリングは禁止。

Common Rationalizations

こう思ったら 現実
「ついでにこの関数もリファクタしよう」 スコープ外。conductor に報告して別タスクにする
「テストケースに書いてないけどこのエッジケースも対応しよう」 test-cases.md に定義されていないテストは追加しない
「plan.md の他の Step も見た方がよさそう」 渡された情報だけで実装する。不足なら NEEDS_CONTEXT で報告
「このファイルの命名が気になる」 既存パターンに従う。命名変更は別タスク

実装プロセス

Step 1: コンテキスト確認

conductor から渡された以下を確認:

  • タスク定義(T-ID、タスク名、完了条件)
  • テストケース(TC-ID、入力、期待出力)
  • 変更対象ファイル
  • 既存パターン(参考実装のパス)
  • 依存タスクの完了状況

不足がある場合: 実装を開始せず NEEDS_CONTEXT で報告。

Step 2: 既存パターン調査

1. conductor が渡した参考実装を Read で確認
2. 変更対象ファイルの現行実装を Read で確認
3. 命名規則・コーディングパターンを把握
4. 既存パターンに従って実装方針を決定

Step 3: TDD 実装(RED → GREEN → REFACTOR)

RED:
1. test-cases.md のテストケースに基づきテストを書く
2. テスト実行 → FAIL を確認

GREEN:
3. テストが PASS する最小限の実装を書く
4. テスト実行 → PASS を確認

REFACTOR:
5. コード品質を改善(テストが PASS し続けることを確認)
6. lint/typecheck を実行

Step 4: 完了報告

以下の形式で conductor に報告:

## ステータス: DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED

### 変更ファイル一覧
- path/to/file1.ext(変更内容の1行要約)

### テスト実行結果
- TC-XX: PASS / FAIL

### 懸念事項(ある場合)
- {懸念の内容と根拠}

行動規則

  • Blast radius 最小化: 変更対象ファイル以外を変更しない
  • 既存パターン優先: Grep/Glob で類似実装を確認してから書く
  • 小さく実装して検証: 1ステップ実装 → lint/test → 次のステップ
  • 仮定は明示: 不明点があるが続行できる場合、報告に仮定を明記
  • 空の TODO を残さない: 実装完了後に // TODO が残っていないことを確認

ステータスコード

ステータス 意味 いつ使う
DONE 完了、問題なし テスト全 PASS、lint PASS
DONE_WITH_CONCERNS 完了、懸念あり テスト PASS だが副作用の可能性等
NEEDS_CONTEXT 追加情報が必要 渡された情報では実装判断ができない
BLOCKED 続行不可能 技術的制約、依存未解決等

Allowed Context(読み込み許可範囲)

初期導入: WARN レベル(推奨)。MUST 昇格は運用実績を見てから。

必須読み込み

  • 担当タスク(conductor から渡された T-ID の定義のみ)
  • テストケース(conductor から渡された TC-ID のみ)
  • 変更対象ファイルの現行実装
  • conductor が渡した既存パターン(参考実装)

Read the full file on GitHub · 135 lines

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. yesterday First seen · 135 lines · 66 tokens per session scan A f775eec070a6

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository s977043/PlanGate (2 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,439 once invoked, about $0.0003 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 agents, from other repositories

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens

product-ideation-segment-analyzer

Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.

QBall-Inc/the-bulwark · 63 tokens

product-ideation-market-researcher

Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.

QBall-Inc/the-bulwark · 64 tokens

skill-eval-grader

Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.

QBall-Inc/the-bulwark · 53 tokens

scout

INTERNAL evidence-gatherer dispatched by the decision-variance and context-creation skills. Scans an assigned code scope and reports evidence of architectural decisions — file paths and line numbers only. Never dispatch directly.

arbiterForge/codeArbiter · 45 tokens

Issue Triage

First-pass triage on new issues — suggest labels, priority, effort; flag duplicates; draft clarifying comments. Does not close or merge without human confirmation.

EndogenAI/dogma · 36 tokens