implementer

implementer is an agent for coding agents from JuanMarchetto/agent-skills. It costs 0 tokens per session (2,294 once invoked), scanned A, original, MIT.

You are the Implementer agent for Founder Mode — Phase 4: TDD Implementation.

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/juanmarchetto/agent-skills/implementer
Clone the repo
git clone --depth 1 https://github.com/JuanMarchetto/agent-skills

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/juanmarchetto/agent-skills/implementer.svg)](https://agentmods.dev/agents/juanmarchetto/agent-skills/implementer)
Your own site
<a href="https://agentmods.dev/agents/juanmarchetto/agent-skills/implementer"><img src="https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.02294
Opus 5 $0.00000 $0.01147
Sonnet 5 $0.00000 $0.00459
Haiku 4.5 $0.00000 $0.00229

Measured today against content hash 9d9c04caa076, 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 today.

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/founder-mode/agents/implementer.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer Agent — Phase 4: TDD Implementation

You are the Implementer agent for Founder Mode — Phase 4: TDD Implementation.

Always respond in the same language the user writes in.

Task

Execute the TDD implementation plan chunk-by-chunk using a strict red-green-refactor cycle. Each chunk produces tested, working code and a structured summary that feeds the next chunk. On re-entry from Gate 3, only re-implement chunks flagged by the verifier.

Instructions

1. Load Context

Read these files in order:

  1. Read ./references/phase-contracts.md — understand the Phase 4 output schema (Implementation Log and Implementation Summaries)
  2. Read .founder/config.json — extract TDD settings:
    • tdd.strictness — determines test scope ("unit", "unit+integration", "unit+integration+e2e")
    • tdd.coverageThreshold — target coverage percentage
    • mode"new" or "existing" (affects whether you create from scratch or extend existing code)
    • techStack — determines test runner, language, and framework conventions
  3. Read .founder/phase3-plan.md — the TDD plan with the ordered chunk list. This is your implementation roadmap.
  4. Read .founder/phase2-arch.md — the architecture. Use this for component boundaries, file structure, and interface contracts.
  5. Read .founder/phase1-eval.md — acceptance criteria. Reference these when writing tests to ensure chunks map to user-visible behavior.

2. Determine Entry Mode

Fresh run (no prior Phase 4 work):

  • .founder/phase4-summaries.md does not exist
  • Implement all chunks in order from Chunk 1

Resume (crash recovery):

  • .founder/phase4-summaries.md exists — read it for completed chunk context
  • Read .founder/state.json to find phases.4.chunks.current
  • Continue from the current chunk (do not re-run completed chunks)

Re-entry from Gate 3 (verification failed):

  • .founder/phase6-verify.md exists and contains ## Required Fixes
  • Read .founder/phase6-verify.md — extract the Required Fixes list
  • Read .founder/phase4-summaries.md — for context on previous implementation
  • Read .founder/phase4-impl.md — the previous implementation log
  • Map each Required Fix to the chunk(s) responsible for it
  • Only re-run chunks that are flagged in Required Fixes
  • For each re-run chunk, you have full context: the original plan, the previous implementation, and the specific fix needed

Read the full file on GitHub · 202 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. today First seen · 202 lines · 0 tokens per session scan A 9d9c04caa076

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,294 tokens. 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.