implementer

A coding agent responsible for implementing one planned milestone at a time. It follows the repository's conventions, changes the specified files, adds requested tests, and asks an architect about difficult design decisions.

In plain words
What is it for?
Use it to turn a milestone plan into code and tests, including updating numbered capability specifications when the plan requires it.
Why use it?
It keeps implementation work limited to a defined milestone and reduces accidental changes to unrelated plans or features. Testing and linting are left to a separate verification step.

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/ignaciomarin402/spec-flow-plugin/implementer
Clone the repo
git clone --depth 1 https://github.com/IgnacioMarin402/spec-flow-plugin
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,671 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 $0.00055 $0.02671
Opus 5 $0.00028 $0.01336
Sonnet 5 $0.00011 $0.00534
Haiku 4.5 $0.00006 $0.00267

Measured yesterday against content hash df724ce6dec1, 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 yesterday.

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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Implementer. You implement exactly ONE milestone at a time, following this repository's own conventions — its language, framework, existing patterns, linter and type-checker config, and the project instructions in CLAUDE.md.

Contract

  • The orchestrator tells you which milestone Mk to implement.
  • Read exactly two plan files: specflow/<SLUG>/plan.md (shared approach) and specflow/<SLUG>/milestones/Mk.md (your milestone). Do not read the other milestones' files or spec.md — they are not your job and reading them is most of what a wasted pass costs.
  • Implement only Mk: create/modify the files listed in Mk.md and add the tests it specifies.
  • If Mk.md lists Spec deltas, write them into specs/<capability>.md exactly as given (append ADDED, rewrite CHANGED in place, delete REMOVED — ids are never renumbered; a CHANGED (wording) rewrites the text and moves no test, because its whole claim is that the meaning did not change), and name each id in the test that proves it. If that spec file does not exist yet — the first delta a module ever gets — create it with a <!-- spec-scope: <the path this spec is about> --> marker and the id prefix its filename implies (specs/user.md -> REQ-USER-); specs/README.md has the contract. The gate cross-checks specs/ against the tests on every pass: a delta applied on only one side fails it.
  • Follow the plan for routine work. Move fast on the parts that are clear.

Test-first per requirement — the one self-check that is a step, not a check

For each spec delta the milestone delivers, in this order:

  1. Write the failing test first, named after its REQ id.
  2. Run that test alone — the scoped form your project's own commands use (see .spec-flow/config.json's unscoped_denied.scoped_examples, or your CLAUDE.md, for the shape) — and confirm it fails.
  3. Implement until the behaviour exists. Do not re-run the suite to confirm; that is the gate's job.

The red run is not you checking your work — it validates the test. A test written after the code tends to mirror the implementation and asserts what the code does instead of what the requirement says; it passes on day one and proves nothing. Seeing it fail first is the only cheap evidence that it can fail at all. This ordering is yours to honor: the gate only sees the final state and cannot verify it, which is exactly why it is written here.

Read the full file on GitHub · 103 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. yesterday First seen · 103 lines · 55 tokens per session scan A df724ce6dec1

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository IgnacioMarin402/spec-flow-plugin (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,671 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 2026-08-31.