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.
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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.
[](https://agentmods.dev/commands/thebeardedbearsas/claude-craft/research-context7)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/research-context7"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/research-context7.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00006 | $0.01519 |
| Opus 5 | $0.00003 | $0.00759 |
| Sonnet 5 | $0.00001 | $0.00304 |
| Haiku 4.5 | $0.00001 | $0.00152 |
Grade A, and why
research-context7 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recherche avec Context7 et Web
Tu es un assistant de recherche expert. Tu dois utiliser le MCP Context7 pour accéder à la documentation des librairies et la recherche web pour trouver des informations à jour sur un sujet technique.
Arguments
$ARGUMENTS
Arguments :
- Sujet de recherche ou question technique
- (Optionnel) Librairies spécifiques à consulter
Exemple : /common:research-context7 "Comment implémenter l'authentification OAuth2 avec NextAuth.js" ou /common:research-context7 "Best practices React 19" react,nextjs
MISSION
Étape 1 : Analyser la Demande
Identifier :
- Le sujet principal de la recherche
- Les technologies/librairies concernées
- Le niveau de détail requis
- Les questions spécifiques à répondre
Étape 2 : Utiliser Context7 (MCP)
Context7 permet d'accéder à la documentation à jour des librairies.
Rechercher la documentation
Utiliser l'outil MCP context7 pour :
1. Rechercher la documentation officielle de la librairie
2. Obtenir les exemples de code à jour
3. Consulter les guides et tutoriels officiels
4. Vérifier les API disponibles
Librairies supportées par Context7
Context7 indexe les documentations de nombreuses librairies populaires :
- React, Next.js, Vue, Nuxt, Svelte
- Node.js, Express, Fastify, NestJS
- Python (Django, FastAPI, Flask)
- TypeScript, Tailwind CSS
- Et bien d'autres...
Format de requête Context7
Pour utiliser Context7, je dois :
- Identifier la librairie exacte
- Formuler une requête précise
- Demander des exemples de code si pertinent
Étape 3 : Recherche Web Complémentaire
Utiliser la recherche web pour :
-
Informations récentes (après la date de cutoff de Context7)
- Nouvelles versions
- Breaking changes
- Annonces officielles
-
Discussions communautaires
- Issues GitHub
- Discussions Stack Overflow
- Articles de blog d'experts
-
Comparaisons et alternatives
- Benchmarks
- Comparaisons de solutions
- Retours d'expérience
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.
- 8d ago First seen · 254 lines · 6 tokens per session scan A 261c0b7f23b9
research-context7 is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 5d ago), licensed MIT. It adds 6 tokens to every session and 1,519 once invoked, about $0.0000 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.
Other commands, from other repositories
test-suite
Run comprehensive test suite with coverage analysis.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
standardize-claude-md
Add missing toolkit sections (Related Global Rules, Quick Start) to existing CLAUDE.md.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.