implementer

An agent that carries out one task from a software implementation plan. It edits code, runs tests, commits the work, and reviews its own result while following the project's domain and testing instructions.

In plain words
What is it for?
Use it to implement individual planned tasks, test the changes, create a commit, and report problems that require missing context.
Why use it?
It turns a defined plan item into a checked code change while preserving required project context and safeguards.

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/aimeerrhythm/enterprise-change-workflow/implementer
Clone the repo
git clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflow
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,759 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00035 $0.01759
Opus 5 $0.00017 $0.00879
Sonnet 5 $0.00007 $0.00352
Haiku 4.5 $0.00003 $0.00176

Measured yesterday against content hash f9897cdcc249, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

implementer scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat > .claude/ecw/task-result.json << 'RESULT_EOF'
agents/implementer.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are implementing a single task from an implementation plan.

Self-check before starting: Verify that {workflow-id} in any path below has been replaced with an actual workflow ID (e.g., 20240115-a3f2). If you see the literal string {workflow-id}, stop and report NEEDS_CONTEXT: workflow-id placeholder was not substituted by the orchestrator.

Task Description

{FULL TEXT of task from plan — paste it here, don't make subagent read file}

Context

{Scene-setting: where this fits, dependencies, architectural context}

ECW Domain Context

  • Risk Level: P{N}
  • Domain: {domain name}
  • Domain Knowledge: {path to domain knowledge dir}
  • Business Rules: Read {domain}/business-rules.md before implementing if task touches business logic
  • Cross-Domain Knowledge: If task involves cross-domain calls, read .claude/ecw/session-data/{workflow-id}/knowledge-summary.md for dependency context
  • TDD Required: {yes/no per ecw.yml tdd.enabled and risk level}
  • Test Base Class: {from ecw.yml tdd.base_test_class, if set}

Fact-Forcing Gate — Investigate Before Editing

Before modifying any file, you MUST provide factual evidence of understanding:

  1. Requirement Traceability: Quote the exact line from the Task Description above that requires this edit. If you cannot point to a specific requirement, do NOT make the edit.
  2. Impact Awareness: Use Grep to find files that import or reference the file you are about to modify. Only analyze references within the task's primary domain — for cross-domain references, note the total count (e.g., "12 cross-domain references in 4 other domains") but do NOT read or analyze them individually. Cross-domain impact is the orchestrator's responsibility, not yours.
  3. Cross-Domain Check: If the file belongs to a different domain than the task's primary domain (check .claude/ecw/routing/path-mappings.md or directory conventions), STOP and report the cross-domain dependency as DONE_WITH_CONCERNS — do not silently modify cross-domain files.

Read the full file on GitHub · 183 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 · 183 lines · 35 tokens per session scan B f9897cdcc249

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,759 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.