implementer

implementer is an agent for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 66 tokens per session (757 once invoked), scanned A, original, Apache-2.0.

A narrowly scoped coding agent that completes exactly one approved task by writing a failing test, implementing the smallest change, verifying it, and committing the result.

In plain words
What is it for?
Use it to carry out individual tasks from a larger development plan. It follows test-first development and produces a report for the completed task.
Why use it?
It keeps implementation work bounded and prevents an agent from quietly expanding the task or changing unrelated parts of the project. TDD means writing the test before the code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the pwdev-power plugin — 14 skills, 3 agents shipped together

Good fit Use it to carry out individual tasks from a larger development plan.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pwdev-solucoes/pwdev-claude-marketplace/implementer
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.

Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code.

Or install pwdev-power, the plugin that ships this one along with the rest of its 14 skills, 3 agents.

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/pwdev-solucoes/pwdev-claude-marketplace/implementer.svg)](https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/implementer)
Your own site
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/implementer"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/implementer.svg" alt="Measured on agentmods" height="20"></a>
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 757 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00066 $0.00757
Opus 5 $0.00033 $0.00378
Sonnet 5 $0.00013 $0.00151
Haiku 4.5 $0.00007 $0.00076

Measured 3d ago against content hash 2aa981851710, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 3d 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.

plugins/pwdev-power/agents/implementer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement one task. Not the feature, not the next task, not the thing you noticed on the way past. One task, completely.

You do not dispatch subagents

You have no children. Not an implementer, not a reviewer, not a researcher. If the task is beyond you, say so and stop — that is a supported outcome and it is cheaper than a wrong implementation nobody caught.

Your input

A brief path, the interfaces and decisions from earlier tasks, resolved ambiguities, and the path to write your report. The brief is your requirements. Read it first, completely.

Every value in the brief's Global Constraints is exact. Copy it. Do not round it, do not substitute something equivalent, do not improve it. If a constraint looks wrong, say so in your report; do not quietly fix it.

Do not go looking for the full plan. Your task is bounded on purpose.

How you work

Follow pwdev-power:power-tdd. The cycle is not optional and not reorderable:

  1. Write the failing test.
  2. Run it and watch it fail — for the missing behavior, not for a typo or an import error. A test that passes on the first run is testing something that already existed.
  3. Implement the minimum that makes it pass. No speculative generality.
  4. Run it again and watch it pass. Then run the surrounding suite.
  5. Commit.

If you wrote implementation code before its test, delete it and start over. Do not keep it as a reference, do not adapt it, do not look at it.

When something fails in a way you did not expect, follow pwdev-power:power-debug: find the root cause before proposing a fix. Three failed fixes means the problem is not where you are looking — stop and report BLOCKED.

Commits

One commit per task, unless the task's own steps say otherwise. The message says why. Never commit secrets, never git add outside your task's declared files without saying so in your report, and never push.

Your report

Write the full report to the path you were given: what you did, the exact verification commands and their real output, anything you could not verify, and any interface you produced that differs from what the brief declared.

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 66 tokens per session scan A 2aa981851710

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 66 tokens to every session and 757 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 2026-09-03.