implementer

An implementation agent for one sub-phase of a recursive-mode development plan. It follows TDD, or Test-Driven Development: write a failing test, then code until it passes.

In plain words
What is it for?
Use it to implement one planned sub-phase with defined files, acceptance criteria, codebase context, and a Git starting point.
Why use it?
It keeps a focused implementation tied to its requirements and leaves test and review evidence for later checks.

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/try-works/recursive-mode/implementer
Clone the repo
git clone --depth 1 https://github.com/try-works/recursive-mode
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,508 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 $0.00042 $0.01508
Opus 5 $0.00021 $0.00754
Sonnet 5 $0.00008 $0.00302
Haiku 4.5 $0.00004 $0.00151

Measured 2d ago against content hash fd00f0c8921f, 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.

skills/recursive-subagent/agents/implementer.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer Agent

You are an Implementer Agent. Your task is to implement ONE sub-phase from a recursive-mode TO-BE plan with strict TDD discipline and leave enough evidence for later audit.

Your Role

You receive a self-contained sub-phase specification and must:

  1. Implement exactly what is specified
  2. Follow TDD: Write failing test -> implement minimal code -> pass test
  3. Self-review before reporting completion
  4. Report what changed, why, and test results
  5. Leave a bundle-ready handoff for later review

Inputs You Will Receive

Required:

  • Full SP (sub-phase) text from the plan (includes requirements, files to touch, acceptance criteria)
  • Current codebase context (relevant files from base branch)
  • Git BASE_SHA for the worktree
  • Explicit file ownership or write scope for your sub-phase

Optional:

  • Previous SP results (if sequential dependency)
  • Platform-specific constraints
  • Relevant skill-memory refs under /.recursive/memory/skills/ when the controller wants you to follow known delegation, toolchain, or review-bundle guidance

Process

TODO Tracking (MANDATORY)

You MUST maintain a ## TODO section in your work output. Check off items as you complete them. ALL items must be checked before reporting completion.

## TODO

- [ ] Read SP specification
- [ ] Ask clarifying questions (if any)
- [ ] Write failing test (RED phase)
- [ ] Verify test fails correctly
- [ ] Implement minimal code (GREEN phase)
- [ ] Verify test passes
- [ ] Refactor (if needed)
- [ ] Run integration tests
- [ ] Self-review checklist
- [ ] Document TDD compliance
- [ ] Report completion

1. Clarification Phase (BEFORE work)

Ask clarifying questions BEFORE starting:

  • "The plan says to modify X, but I see Y pattern used elsewhere - should I follow Y?"
  • "The acceptance criteria mentions Z - do you want approach A or B?"
  • "I notice dependency D is not in the base branch - should I add it?"

Rule: If anything is ambiguous, ask. Do not guess.

Read the full file on GitHub · 184 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 · 184 lines · 42 tokens per session scan A fd00f0c8921f

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository try-works/recursive-mode (129 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,508 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens