implement

A command for planning, building, and evaluating a software feature through separate roles. It accepts either a free-form idea or a GitHub issue number or URL.

In plain words
What is it for?
Use it to turn an idea or issue into an implementation, while checking the project context and existing code patterns first.
Why use it?
It gives feature work a defined process and reduces the risk of one step judging its own result.

Command 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 commands/steve-magne/hookstack/implement
Clone the repo
git clone --depth 1 https://github.com/steve-magne/hookstack

Made for: Claude Code.

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 1,413 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 $0.00000 $0.01413
Opus 5 $0.00000 $0.00707
Sonnet 5 $0.00000 $0.00283
Haiku 4.5 $0.00000 $0.00141

Measured yesterday against content hash 1a9011dd6e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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.

.claude/commands/implement.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement — Planner → Generator → Evaluator

Conçoit (si user-facing) puis livre une feature, selon le pattern à 3 rôles séparés (anti-biais d'auto-éval). Deux sources d'entrée — le mode est déduit de l'argument :

$ARGUMENTS =

  • une idée libremode idée (flux rapide) : /implement "ajouter un filtre par provider sur le catalogue". Raffinage live + dev immédiat dans cette session, sans passer par GitHub.
  • un numéro / URL d'issuemode issue : /implement 88. Lire son contenu avec gh issue view <N> pour cadrer le Contrat d'implémentation.

0. Cadrage du contexte projet (déterministe, ~0 token)

Avant de planifier, s'ancrer dans le projet sans charger de code en contexte principal : node scripts/okf.mjs query <termes de la feature> (retrieval déterministe). N'escalader au sous-agent okf-librarian (lit dans son propre contexte → renvoie une synthèse courte) que si la query ne suffit pas. Objectif : le Planner connaît contraintes + patterns existants (Motion, registre, CLI, conventions, cohérence 4 surfaces) avant d'écrire le Contrat — pas de lecture exploratoire du code en contexte principal. C'est le levier principal d'économie de tokens : chaque lecture lourde se fait dans le contexte d'un sous-agent, jamais dans le tien.

0.5 Design Brief (conception multi-perspectives) — features user-facing uniquement

Sauter pour un fix purement technique (pas d'écran/UX impacté) — dis-le en une ligne. Sinon, fan-out parallèle sur des lentilles indépendantes, chacune lit son OKF dans son propre contexte :

  • frontend-engineer → où l'utilisateur le voit, hiérarchie visuelle, Motion (m.*, tokens motion.ts), accessibilité.
  • lentille produit/cohérence (general-purpose ou okf-librarian) → sert la promesse produit ? Impact sur les 4 surfaces (site / CLI / doc/product/ / README.md) ?

Chaque lentille renvoie 2-3 lignes max (proposition + 1 risque). Tu synthétises un Design Brief de 5-8 lignes (où ça vit · feedback clé · 1 garde-fou UX ou de cohérence). Il devient un input du Contrat d'implémentation ci-dessous. Garde-fou anti-scope-creep : le brief sert l'intention de départ (l'idée, ou le périmètre de l'issue), il ne la gonfle pas.

Read the full file on GitHub · 78 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 · 78 lines · 0 tokens per session scan A 1a9011dd6e75

Subscribe to this mod's changes

implement is a command published in the GitHub repository steve-magne/hookstack (7 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,413 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 2026-08-31.