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/aphrody-code/bxc/sync-claudegit clone --depth 1 https://github.com/aphrody-code/bxcWhat 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 | $0.00060 | $0.01603 |
| Opus 5 | $0.00030 | $0.00801 |
| Sonnet 5 | $0.00012 | $0.00321 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
sync-claude 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sync-claude — audit + update CLAUDE.md selon les guidelines Anthropic
Tu vas faire un audit COMPLET puis appliquer des updates ciblés sur les CLAUDE.md
du repo. Scope = $ARGUMENTS (défaut all).
Principes officiels Anthropic (à respecter ABSOLUMENT)
Source : https://docs.claude.com/en/docs/claude-code/memory et le blog "Best practices for Claude Code".
- Concise et human-readable — dense > verbeux. CLAUDE.md fait partie du prompt système : chaque ligne coûte des tokens à chaque tour.
- Actionable — toute commande documentée doit être copy-paste ready. Pas de "you might want to" ni de "consider running". Verbe à l'impératif.
- Project-specific — pas de best practices génériques (TypeScript strict est un détail projet, "use TypeScript correctly" est du bruit).
- Non-obvious gotchas first — ce que le code ne révèle pas en lecture directe : ordre de chargement, side-effects, contraintes hardware, etc.
- Sections recommandées (utiliser SEULEMENT celles qui apportent) :
Commands·Architecture·Key Files·Code Style·Environment·Testing·Gotchas·Workflow. Pas de remplissage. - DRY via
@path— la syntaxe@GEMINI.mdimporte un autre fichier au chargement. Préférer ça à la duplication de doc. - Pas de duplication entre niveaux — CLAUDE.md package ne répète pas CLAUDE.md racine. Il ne contient QUE le delta propre au package.
Étape 1 — Discovery
Trouve tous les CLAUDE.md du projet (exclure vendor/, node_modules/,
vendor/mcp-sdk-typescript/) :
find . -name "CLAUDE.md" -not -path "*/node_modules/*" -not -path "*/vendor/*/CLAUDE.md" 2>/dev/null
Filtre selon $ARGUMENTS :
root→ seul./CLAUDE.mdpackages→ seuls./packages/*/CLAUDE.mdall(défaut) → tout
Étape 2 — Capture l'état RÉEL du projet
Pour chaque CLAUDE.md à auditer, capture la vérité terrain :
# scripts dispo (commands à documenter)
jq -r '.scripts | keys[]' package.json # ou ./packages/X/package.json
# layout réel (sections Architecture / Key Files)
ls -la src/ packages/ scripts/ benchmarks/ 2>/dev/null
# tests et leur point d'entrée
find test -name '*.test.ts' | head -5
# entry points réels (vs stubs)
grep -l "Bun.serve\|\.listen(\|export default" src/*.ts packages/*/src/*.ts 2>/dev/null
# état git pour repérer les fichiers récemment renommés/supprimés
git log --diff-filter=D --name-only --pretty=format: -20 | sort -u
git log --diff-filter=R --name-status -10
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.
- yesterday First seen · 144 lines · 60 tokens per session scan A b8604f44aab1
sync-claude is a command published in the GitHub repository aphrody-code/bxc (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,603 once invoked, about $0.0003 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 2026-08-31.
Other commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
feature
End-to-end feature/bug-sweep workflow for ui-debugger-mcp — understand, reproduce against a real target, explore in parallel, split into path-disjoint slices, build with a hive of agents in this ONE checkout (never worktrees), gate green, PR, merge, release to npm. Tracks in GitHub issues. Reads intent from the prompt.