agentmods.dev

audit-freshness

audit-freshness is a command for Claude Code from TheBeardedBearSAS/claude-craft. It costs 23 tokens per session (2,106 once invoked), scanned A, original, MIT.

A review of whether project instructions and references still match current versions and recommended practices across several technology stacks. It uses official documentation and web research.

In plain words
What is it for?
Use it to check stacks such as Symfony, React, Flutter, Python, Angular, Laravel, Vue.js, React Native, C# and PHP, either together or in selected groups.
Why use it?
It helps locate outdated framework or tool information without changing the project's instructions automatically.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

not rated 105repo 6d ago A scan 23 tokens original MIT

Good fit Use it to check stacks such as Symfony, React, Flutter, Python, Angular, Laravel, Vue.js, React Native, C# and PHP, either together or in selected groups.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thebeardedbearsas/claude-craft/audit-freshness
View source ↗ TheBeardedBearSAS/claude-craft
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.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

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 audit-freshness

README.md
[![agentmods](https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/audit-freshness/github.svg)](https://agentmods.dev/commands/thebeardedbearsas/claude-craft/audit-freshness)
Your own site
<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/audit-freshness"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/audit-freshness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-freshness

Your own site · 80×15
<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/audit-freshness"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/audit-freshness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,106 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00023 $0.02106
Opus 5 $0.00012 $0.01053
Sonnet 5 $0.00005 $0.00421
Haiku 4.5 $0.00002 $0.00211

Measured 9d ago against content hash f9907926e4eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-freshness 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 9d 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.

.claude/commands/common/audit-freshness.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit de Fraîcheur claude-craft

Orchestre une équipe de 17 agents parallèles pour vérifier que l'ensemble des skills, commands, agents, references et rules du projet sont alignés avec les dernières versions stables et best practices 2026 des frameworks/outils déclarés. Utilise le MCP Context7 (mcp__context7__resolve-library-id + query-docs) et WebSearch pour les release notes officielles.

Résultat : rapport consolidé docs/audit/freshness-YYYY-MM-DD.md — aucune modification automatique des skills/commands/refs.

Arguments

$ARGUMENTS

  • --wave=1|2|3|all (défaut all) : exécuter uniquement une vague donnée
  • --stack=<nom> : limiter la vague 1 à un stack (symfony, react, flutter, python, angular, laravel, vuejs, reactnative, csharp, php)

MISSION

Étape 1 — Préparer le rapport cible

  1. Déterminer la date du jour (format YYYY-MM-DD)
  2. Créer docs/audit/freshness-<date>.md avec un en-tête (version claude-craft, date, nombre d'agents lancés, légende écarts : critique/majeur/mineur/aucun)
  3. Relire .claude/CLAUDE.md (table versions) et .claude/COMPATIBILITY.md pour la source de vérité des versions déclarées

Étape 2 — Vague 1 : Stacks techniques (10 agents EN PARALLÈLE)

Lancer les 10 agents dans UN SEUL message (10 tool_use Task/Agent). Chaque agent reçoit ce prompt (adapter <STACK>) :

Tu audites la fraîcheur du stack <STACK> dans le dépôt claude-craft.

ÉTAPES :
1. Lire la version déclarée du framework/langage <STACK> dans :
   - .claude/CLAUDE.md (table Supported Technologies)
   - .claude/references/<stack>/CLAUDE.md et project-context.md
   - .claude/agents/<stack>-reviewer.md (frontmatter + body)
   - Skills .claude/skills/<stack>-*/SKILL.md
   - Commandes .claude/commands/<stack>/*.md

2. Via mcp__context7__resolve-library-id puis mcp__context7__query-docs,
   récupérer la version stable actuelle + patterns recommandés 2026.

3. Via WebSearch, vérifier les release notes officielles (site officiel,
   GitHub releases) — confirmer version stable, breaking changes, nouvelles
   best practices (ex: signals Angular, async Symfony Messenger, etc.).

4. Identifier :
   - Écart de version (déclarée vs stable)
   - Best practices obsolètes dans les skills/refs/commands
   - Patterns nouveaux absents du repo (ex: React Compiler, Flutter Impeller)

5. Retourner EXACTEMENT ce format Markdown (<300 mots) :

## <STACK>
- **Version déclarée** : X.Y (source: <path>:<line>)
- **Version stable actuelle** : X.Y (source: <context7-lib-id> ou <URL>)
- **Écart** : aucun | mineur | majeur | critique
- **Best practices à revoir** :
  - <finding> — source: <URL ou context7 ID>
- **Patterns manquants** :
  - <pattern> — source: <URL>
- **Fichiers claude-craft impactés** : <path1>, <path2>, ...
- **Sources consultées** : context7=<ids> / web=<urls>

CONTRAINTE : citer systématiquement les sources. Ne rien inventer. Si une
info n'est pas trouvée, écrire "non trouvé" explicitement.

Read the full file on GitHub · 177 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. 9d ago First seen · 177 lines · 23 tokens per session scan A f9907926e4eb

Subscribe to this mod's changes

audit-freshness is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 2,106 once invoked, about $0.0001 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.

Claude CodeCode reviewResearchagentsai-toolsbmadclean-architectureddd
Related

Other commands, from other repositories

assemble-team

Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.

travisjneuman/.claude · 25 tokens

review-code

Trigger a comprehensive code review on recent changes or specified files.

travisjneuman/.claude · 11 tokens

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

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.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens