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.
npx agentmods add commands/thebeardedbearsas/claude-craft/fixgit 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/fix)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/fix"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/fix.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 | $0.00011 | $0.02557 |
| Opus 5 | $0.00005 | $0.01278 |
| Sonnet 5 | $0.00002 | $0.00511 |
| Haiku 4.5 | $0.00001 | $0.00256 |
Grade A, and why
fix 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 today.
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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Recette Fix - Correction Automatisee des Bugs
Complement de /qa:recette. Lit un rapport/session de recette, affine chaque erreur pour la rendre exploitable, genere les documents de project management (stories BMAD, backlog, sprint), puis lance la correction TDD pour chaque bug. Implemente la Regle d'Or : Un bug corrige ne doit JAMAIS reapparaitre.
Arguments
$ARGUMENTS
--session=<id>: ID de session recette (ex: REC-20260130-143022) [requis]--dry-run: Affiner les erreurs et generer les documents BMAD sans corriger--severity=<level>: Filtrer par severite minimum (critical, high, medium, low)--skip-fix: Generer uniquement les documents, pas de correction TDD--auto-commit: Commit automatique apres chaque bug corrige
Fonctionnalites Cles
| Fonctionnalite | Description |
|---|---|
| Affinage des Erreurs | Analyse la cause racine, reproduit via Chrome si disponible |
| Groupement Intelligent | Deduplique les erreurs par cause racine commune |
| Documents BMAD | Genere des bug stories, met a jour backlog et sprint |
| Correction TDD | Workflow RED → GREEN → REFACTOR pour chaque bug |
| Tests de Regression | Generation automatique et mise a jour du registre |
| Suivi de Progression | fix-state.yaml pour reprise et monitoring |
Processus en 7 Phases
Session recette (.recette/sessions/{id}/)
|
v
Phase 1: Charger la session et les erreurs
|
v
Phase 2: Affiner les descriptions d'erreurs
| - Reproduire via Chrome si besoin
| - Identifier la cause racine
| - Classifier severite
|
v
Phase 3: Grouper par cause racine
| - Deduplication
| - Priorisation
|
v
Phase 4: Generer les documents BMAD
| - Bug stories (US-XXX-bug-YYY)
| - Mise a jour backlog
| - Mise a jour sprint-status.yaml
|
v
Phase 5: Correction TDD par bug
| - RED: test qui reproduit le bug
| - GREEN: correction minimale
| - REFACTOR: amelioration
|
v
Phase 6: Verification
| - Tous les tests passent
| - Tests de regression generes
| - Registre regression mis a jour
|
v
Phase 7: Rapport de synthese
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.
- today First seen · 288 lines · 11 tokens per session scan A c0aa93e1da30
fix is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 2,557 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 2026-09-03.
Other commands, from other repositories
testarch-atdd
Generate failing acceptance tests using TDD cycle. Use when the user says ""lets write acceptance tests"" or ""I want to do ATDD"".
testarch-atdd
Generate failing acceptance tests before implementation using TDD red-green-refactor cycle.
implement
E2E-first Test driven development — unit tests written last.
test-engineer
Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows.
qa
在真实线上环境跑测并验收一张 Workflow 单据（只跑测和验收，不改代码）.
test
Write tests before implementation using Red-Green-Refactor.