okf

A command for consulting and maintaining OKF, a project knowledge bundle containing architecture, vision, marketing, roadmap, and coding conventions. It directs each request to the relevant information.

In plain words
What is it for?
Use it to look up a project topic, add or improve knowledge, check outdated entries, validate the bundle, rebuild its indexes, or inspect links between documents.
Why use it?
It prevents the agent from loading every project document into its working context. This reduces unnecessary reading while keeping responses tied to project guidance.

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/okf
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 699 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 $0.00699
Opus 5 $0.00000 $0.00349
Sonnet 5 $0.00000 $0.00140
Haiku 4.5 $0.00000 $0.00070

Measured yesterday against content hash 23665ec36ed4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

okf 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/okf.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OKF — Connaissance projet (consulter & maintenir)

Bundle de connaissance OKF dans okf/ : source de vérité (architecture, vision, marketing, roadmap, conventions). Cette commande aiguille vers le bon usage selon $ARGUMENTS.

Optimisation tokens — principe

Ne jamais charger tout le bundle dans le contexte principal. Deux leviers :

  1. Retrieval déterministe (node scripts/okf.mjs query ...) — ~0 token modèle.
  2. Délégation au sous-agent okf-librarian — il lit dans son propre contexte et ne renvoie qu'une synthèse. Préférer ça dès que la réponse demande plus d'un concept.

Routage selon $ARGUMENTS

(vide) ou consult <sujet> — consulter

Déléguer au sous-agent okf-librarian : « Donne le contexte OKF pour : <sujet> ». Il renvoie réponse + sources + points à vérifier. Pour un besoin trivial mono-concept, node scripts/okf.mjs query <sujet> puis lire le seul fichier en tête suffit.

enrich — passe d'enrichissement

  1. node scripts/okf.mjs stale — confirmer la péremption.
  2. Déléguer à okf-librarian en mode ENRICHISSEMENT (cf. okf/meta/self-improvement.md).
  3. Vérifier node scripts/okf.mjs validate → OK, et qu'une entrée a été ajoutée à okf/log.md.

check — santé du bundle

node scripts/okf.mjs validate --strict   # liens cassés + champs recommandés inclus
node scripts/okf.mjs stale

validate accepte --json (CI/automatisation). Erreurs dures = §9.1/§9.2 ; warnings = liens cassés (tolérés §5.3), champs recommandés manquants, frontmatter des fichiers réservés. --strict rend les warnings fatals.

map — catalogue complet compact

node scripts/okf.mjs map

graph — graphe HTML interactif autonome

node scripts/okf.mjs graph            # écrit okf/graph.html (versionné dans le repo)
node scripts/okf.mjs graph -o /tmp/okf.html

Régénérer après tout ajout/suppression de concept ou de lien, comme index. Concepts = nœuds (couleur par type), liens markdown = arêtes ; panneau détail avec liens sortants / cité par, filtre par type, recherche. Ouvrir le .html dans un navigateur.

Read the full file on GitHub · 58 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 · 58 lines · 0 tokens per session scan A 23665ec36ed4

Subscribe to this mod's changes

okf 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 699 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.