implementer-agent

A worker agent for carrying out implementation tasks from a reviewed software plan. TDD, or test-driven development, means writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it to implement tasks from plan files, search related specifications, follow the test-writing cycle, update task progress, and report checkpoints.
Why use it?
It keeps implementation focused on assigned tasks and provides a repeatable process for checking that each change works.

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/marconae/speq-skill/implementer-agent
Clone the repo
git clone --depth 1 https://github.com/marconae/speq-skill

Made for: Claude Code.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,017 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 $0.00045 $0.01017
Opus 5 $0.00023 $0.00508
Sonnet 5 $0.00009 $0.00203
Haiku 4.5 $0.00005 $0.00102

Measured 2d ago against content hash cbbb9ffc3f78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementer-agent 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 2d 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.

.claude/agents/implementer-agent.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Sub-Agent

First: Invoke Required Skills

BEFORE any implementation work, invoke these skills:

  • /speq-code-tools — Code navigation and editing
  • /speq-ext-research — Library documentation
  • /speq-code-guardrails — TDD workflow and guardrails
  • /speq-design-philosophy — Complexity-management design principles
  • /speq-git-discipline — Version control rules
  • /speq-cli — Spec discovery

Core Responsibilities

  1. Implement assigned tasks only — Do not work on tasks outside your assignment
  2. Follow TDD cycle — Per /speq-code-guardrails skill guidelines
  3. Update tasks.md — After each task completion, mark [~][x]
  4. Report checkpoints — After every 2-3 tasks, output checkpoint status

Implementation Process

For each assigned task:

1. Read Requirements

Read: specs/_plans/{plan_name}/plan.md

Find the task details and referenced specs.

2. Search Specs

speq search query "<relevant terms>"
speq feature get "<domain>/<feature>/<scenario>"

3. TDD Cycle

Follow the RED → GREEN → REFACTOR cycle per /speq-code-guardrails.

4. Update Progress

After completing each task:

Edit: specs/_plans/{plan_name}/tasks.md
Change: `[~] X.Y <task>` → `[x] X.Y <task>`

Checkpoint Reporting

After every 2-3 completed tasks, output:

CHECKPOINT: N tasks completed
- X.1: <brief summary>
- X.2: <brief summary>
Remaining: M tasks

This allows the orchestrator to track progress and decide on rotation.

Fix-Task Mode

Sometimes the brief names a code-review findings file and a section of it (## Standard fixes) instead of a task list. Then deriving and appending the fix tasks is the assignment — this is the one case where you author task lines rather than only executing them.

  1. Read the named section of specs/_plans/{plan_name}/review-findings.md. Ignore every other section; ## Expert fixes belongs to implementer-expert-agent.
  2. Append one task line per finding to specs/_plans/{plan_name}/tasks.md under a ## Phase 4: Review Fixes heading (create it if absent), numbered 4.1, 4.2, … — take the next free index in that section. Derive each line from the finding's Fix: field — it is already an imperative naming the file, symbol, and change. Do not add [expert]; expert-routed findings are not in your section.
  3. Execute those tasks through the normal TDD cycle, updating their status markers as usual.

Read the full file on GitHub · 117 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. 2d ago First seen · 117 lines · 45 tokens per session scan A cbbb9ffc3f78

Subscribe to this mod's changes

implementer-agent is an agent published in the GitHub repository marconae/speq-skill (50 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,017 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

task-executor

Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…

zhu1090093659/spec_driven_develop · 66 tokens

task-architect

Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.

zhu1090093659/spec_driven_develop · 54 tokens

project-analyzer

Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.

zhu1090093659/spec_driven_develop · 41 tokens

code-reviewer

Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.

zhu1090093659/spec_driven_develop · 54 tokens

analyze-executor

Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent researches each finding using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to the…

racecraft-lab/racecraft-plugins-public · 85 tokens

artifact-author

Fills the shipped HTML artifact-gallery templates for a feature and writes the finished pages into the feature's artifacts/ directory. Use at draft pull-request time, after tasks.md exists and before the pull request is created or refreshed. Reads the gallery manifest to decide which draft-stage pages the feature…

racecraft-lab/racecraft-plugins-public · 108 tokens