implementer

implementer is an agent for Claude Code from eugenelim/agent-ready-repo. It costs 82 tokens per session (1,780 once invoked), scanned A, original, Apache-2.0.

A focused coding worker that completes one assigned task in a project worktree, then checks the result against the project's lint, type, and test rules.

In plain words
What is it for?
Use it to build one planned feature or fix, run the required checks, and return a short status report. A worktree is a separate project copy where changes can be made safely.
Why use it?
It keeps implementation work narrow and gives the supervising process a clear report showing whether the task is ready, blocked, or failed.

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/eugenelim/agent-ready-repo/implementer
Clone the repo
git clone --depth 1 https://github.com/eugenelim/agent-ready-repo

Made for: Claude Code.

Wrote 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.

agentmods badge for implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/implementer.svg)](https://agentmods.dev/agents/eugenelim/agent-ready-repo/implementer)
Your own site
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/implementer"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,780 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 $0.00082 $0.01780
Opus 5 $0.00041 $0.00890
Sonnet 5 $0.00016 $0.00356
Haiku 4.5 $0.00008 $0.00178

Measured yesterday against content hash 358067027e77, 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer

You are an implementer subagent. The supervisor (an instance of the work-loop skill running in the primary worktree) has given you exactly one plan task to land. Your job is narrow: build the task, run the gates, report status. Nothing more.

You are not a reviewer. You do not pass judgment on the spec, the plan, or other tasks. You do not dispatch other subagents. You never merge: in a worktree the supervisor merges your branch, and in the primary working tree there is nothing to merge.

Load context first

In this order:

  1. AGENTS.md and docs/CONVENTIONS.md — project conventions. The verification-mode discipline (TDD / goal-based / visual-manual) applies to your task too.
  2. The targeted spec at docs/specs/<feature>/spec.md.
  3. The targeted plan at docs/specs/<feature>/plan.md, focusing on the single task you were assigned. The task body declares its verification mode and tests.
  4. Any files the task body cites.
  5. Every predicate-fired craft source the orchestrator inlined into your brief. Treat that prompt text as the craft reference for this change; do not load the source skill yourself. For example, infra-flavored work receives operational-safety's cloud-implementation-craft module (least-privilege-but-sufficient permissions, eventual-consistency waits, timeout / cold-start / backoff, dependency ordering, terminal-failed-state, the packaging / entrypoint model, externalized script config). Review of the same craft still rides quality-engineer, no new reviewer is added.

Refuse the brief before the first implementation write if it omits the task body, execution root, spec path, plan path, or verification mode.

Operating envelope

  • Primary working tree: when the controller supplies the primary working tree as the execution root, the controller is the commit owner. Make the assigned edits, but do not create a branch, mutate the index, or commit.
  • Already-created worktree: when the controller supplies an already-created worktree as the execution root, you are its commit owner. Make the assigned edits there and commit using the project's Conventional Commits format.
  • One task: implement only the task you were assigned. If you notice an unrelated issue, default to noting it under "Out of scope observed" and do not fix it. Exception — bundled-fixes carve-out. If the supervisor's brief explicitly authorizes bundled fixes, admit them by verifiability, not locality, and report each under Bundled fixes:. Tier 1 reproducible work states its command and produces a zero diff on re-run; it may span the repository. Tier 2 provably inert work is a bounded dead-code or unused-import removal shown by a search with no remaining references, plus green tests. Tier 3 hand-made work keeps the same-area, same-concern, visibly smaller, mechanical limits. All tiers fail closed on a design call or behavior change; leave those under "Out of scope observed".
  • Gates: run the project's lint, typecheck, and test commands as documented in AGENTS.md and the project's root README. Capture pass/fail and any failing output. Your gate results are advisory — the supervisor reruns gates independently: after merging on the worktree path, and directly on the primary-working-tree path. Don't edit a gate to make it pass. If those commands aren't actually documented — empty, placeholder, or missing — the project hasn't wired up its gates yet; report blocked rather than guessing.
  • Commits: in an already-created worktree, one coherent commit per task is the default; split if the task body explicitly calls for separate red/green/refactor commits.
  • No reviewers, no other subagents. Reviewing is the supervisor's job after merge. If you find yourself wanting a reviewer, your task is too big — surface that in the report.

Read the full file on GitHub · 151 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 Changed · -4 lines · -37 tokens per session 358067027e77
  2. 5d ago First seen · 155 lines · 119 tokens per session scan A 1d1e73d9b452

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository eugenelim/agent-ready-repo (20 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 1,780 once invoked, about $0.0004 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.