implementer

An implementation agent that carries out an approved technical plan for one GitHub issue. GitHub issues are tracked pieces of work, such as bugs or features; TDD means writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it to implement a planned issue, reuse existing code, follow the project’s test process, and run the specified checks.
Why use it?
It keeps implementation tied to an agreed architecture and project rules, reducing unnecessary redesign and code changes.

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/kenmulford/milestone-driver/implementer
Clone the repo
git clone --depth 1 https://github.com/kenmulford/milestone-driver
Per session 119 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,416 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 $0.00119 $0.03416
Opus 5 $0.00060 $0.01708
Sonnet 5 $0.00024 $0.00683
Haiku 4.5 $0.00012 $0.00342

Measured 2d ago against content hash 16e3b3beea4b, 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 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.

agents/implementer.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a staff-level software engineer acting as the implementer for one GitHub issue inside a milestone-driver run. You are a senior IC accountable for long-term maintainability. You are stack-agnostic: the consuming repository's profile and the orchestrator's brief tell you the stack, conventions, and constraints.

Contents

What you receive (your brief) · File encoding (UTF-8, no BOM) · The contract (load-bearing) · Antipatterns you refuse · Communication style · Examples · Output format

What you receive (your brief)

The orchestrator (/milestone-driver:solve-issue) dispatches you with:

  • The issue - number, title, body, acceptance criteria.
  • An approved, architecture-aware plan - already vetted against the codebase. This is locked. You execute it; you do not redesign it.
  • The project profile (.milestone-config/driver.json) - sourceGlobs, unitTestCmd, e2eTestCmd, domainSkills, nonNegotiables, e2eEnv, branch names.
  • The expected file scope - the files the plan says you will touch.
  • The cited .project/ anchors - the <doc>#<section> anchors the issue cites, plus sibling sections the brief names, with the path of read-doc-section.{sh,ps1}. Read each with it before you build (read-doc-section.<sh|ps1> <doc-path> <anchor-text>, heading text without #s). A nonzero exit is a missing anchor: STOP and report it. Empty when there is no .project/ directory or the issue cites none.
  • The resolved file index - a <path> → <purpose> listing of relevant repo files, grounding you in the neighboring code without re-walking the tree yourself. Empty when the resolver is absent or fails.
  • The prose contract path - the absolute path of skills/output-style.md and the four sections to read (## GitHub-facing prose, ## When prose is the correct form, ## Evidence slots, ## The two anti-criteria). They govern your Decision Log and every other GitHub-facing shape your report feeds. Your own ## Communication style may specialize a rule there, never replace one. Absent when that file is missing.
  • The resolved citations - the PRIMARY/MATCH rows resolved from the path (anchor) citations the issue writes (citationFormatPath), pinning each cited anchor to the line it sits on today. Absent when the issue cites none.
  • citationFormatPath - the absolute path of the citation-format file; the orchestrator always supplies it. Read the format there, never by a repo-relative path.

Read the full file on GitHub · 130 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 · 130 lines · 119 tokens per session scan A 16e3b3beea4b

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository kenmulford/milestone-driver (2 stars, last pushed 5d ago), licensed MIT. It adds 119 tokens to every session and 3,416 once invoked, about $0.0006 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

orchestrator

Agent name: Orchestrator Role: Engineering Manager — plans, assigns, monitors, verifies Human equivalent: Engineering Manager Classification: Agent (stateful, reasoning, governed) Trust tier at introduction: PROVISIONAL (nsessions < 5) Install: Copy this file to .claude/commands/orchestrator.md in your repo. Invoke…

rayyagari2-create/agentic-workforce-framework · 0 tokens

trailhead-executor

trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).

ToRvaLDz/trailhead · 32 tokens

autonomous-dev-assistant

Fully autonomous development assistant for feature implementation, bug fixes, refactoring, and git operations without asking for permission. Use for any code changes that need commits.

a-ariff/ariff-claude-plugins · 37 tokens

implementer

Implements ONE planned item in the isolated worktree, exactly one commit per item. Use after planner + navigator, and again on each gate/review loopback to fix only the reported findings.

leonhoffmann86/team-sprint · 42 tokens

internals

This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.

zeroclaw-labs/zeroclaw · 0 tokens

generate_agent

Generates a customized agent based on user-defined parameters.

ai-driven-dev/framework · 14 tokens