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/pre-merge-check)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/pre-merge-check"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/pre-merge-check/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.
<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/pre-merge-check"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/pre-merge-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01616 |
| Opus 5 | $0.00003 | $0.00808 |
| Sonnet 5 | $0.00001 | $0.00323 |
| Haiku 4.5 | $0.00001 | $0.00162 |
Grade A, and why
pre-merge-check 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 11d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vérification Pre-Merge
Tu es un assistant de qualité code. Tu dois effectuer toutes les vérifications nécessaires AVANT de merger une branche, pour garantir la qualité et éviter les régressions.
Arguments
$ARGUMENTS
Arguments attendus :
- Branche source (défaut: branche courante)
- Branche cible (défaut: main ou master)
Exemple : /common:pre-merge-check feature/auth main
MISSION
Étape 1 : Analyser le Diff
# Identifier les branches
SOURCE_BRANCH=$(git branch --show-current)
TARGET_BRANCH=${2:-main}
# Commits à merger
git log $TARGET_BRANCH..$SOURCE_BRANCH --oneline
# Fichiers modifiés
git diff $TARGET_BRANCH...$SOURCE_BRANCH --stat
# Lignes ajoutées/supprimées
git diff $TARGET_BRANCH...$SOURCE_BRANCH --shortstat
Étape 2 : Vérifications de Qualité
2.1 Tests Complets
# Exécuter TOUS les tests
# Symfony
docker compose exec php vendor/bin/phpunit --coverage-text
# Flutter
docker run --rm -v $(pwd):/app -w /app dart flutter test --coverage
# Python
docker compose exec app pytest --cov --cov-report=term
# React/RN
docker compose exec node npm run test -- --coverage
2.2 Analyse Statique Complète
# PHPStan (niveau max)
docker compose exec php vendor/bin/phpstan analyse -l max
# Dart Analyzer
docker run --rm -v $(pwd):/app -w /app dart dart analyze --fatal-infos
# Mypy (strict)
docker compose exec app mypy --strict .
# TypeScript
docker compose exec node npx tsc --noEmit
2.3 Vérification Dépendances
# Audit sécurité
# PHP
docker compose exec php composer audit
# Python
docker compose exec app pip-audit
# Node
docker compose exec node npm audit
# Flutter
docker run --rm -v $(pwd):/app -w /app dart dart pub outdated
Étape 3 : Vérifications Spécifiques
Migrations DB (si présentes)
# Vérifier les migrations Doctrine
git diff $TARGET_BRANCH...$SOURCE_BRANCH -- migrations/
# Si migrations présentes
docker compose exec php php bin/console doctrine:migrations:diff --no-interaction
docker compose exec php php bin/console doctrine:schema:validate
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.
- 11d ago First seen · 238 lines · 6 tokens per session scan A 99601e13f856
pre-merge-check is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 8d ago), licensed MIT. It adds 6 tokens to every session and 1,616 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
speckit.companion.living-coverage
Report living-spec requirement→test coverage — per requirement, whether its coverage tier maps a test (opt-in, read-only, never halts).
review-and-refactor
You're a senior expert software engineer with extensive experience in maintaining projects over long time and ensuring clean code and best practices.
converge
Run an unattended review→fix→re-review loop on the current branch until the reviewer has no findings at or above Medium, then push once. Findings stay in a local scratch file and are never posted to GitHub. Stops early on oscillation, a red test suite, or a 4-review cap.
local-code-review-tests
Review uncommitted changes, build projects, and run unit tests.
octo-deliver
"Delivery phase - Review, validate, and test with multi-AI quality assurance".
speckit.verify
Validates implementation completion by checking tasks, logic, tests, and code quality against specifications. Use when you need to verify that all tasks are properly completed.