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 skills add naiersaidane/claude-mastery --skill livregit clone --depth 1 https://github.com/naiersaidane/claude-masteryWrote 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/skills/naiersaidane/claude-mastery/livre)<a href="https://agentmods.dev/skills/naiersaidane/claude-mastery/livre"><img src="https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/livre/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/skills/naiersaidane/claude-mastery/livre"><img src="https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/livre.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 | $0.00090 | $0.00634 |
| Opus 5 | $0.00045 | $0.00317 |
| Sonnet 5 | $0.00018 | $0.00127 |
| Haiku 4.5 | $0.00009 | $0.00063 |
Grade A, and why
livre 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 12d 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.
What it actually says
/livre
Commit tous les changements, synchronise avec main distant, push, et crée une Pull Request.
Étapes
1. Vérification de sécurité
- Exécute
git branch --show-currentpour obtenir la branche courante - Si tu es sur
main, refuse et demande à l'utilisateur de créer d'abord une branche de fonctionnalité (propose/branche)
2. Synchronisation avec main distant
- Récupère la dernière version :
git fetch origin main - Vérifie si la branche est en retard :
git log HEAD..origin/main --oneline - Si en retard sur origin/main, fusionne :
git merge origin/main - En cas de conflits de fusion, montre-les à l'utilisateur et aide à les résoudre avant de continuer
3. Staging et commit
- Exécute
git statuspour voir tous les changements (n'utilise jamais le flag-uall) - Exécute
git diffetgit diff --stagedpour revoir les changements - Exécute
git log --oneline -5pour voir le style des commits récents - Ajoute au staging les fichiers modifiés/nouveaux pertinents (nomme les fichiers précisément, pas
git add -A) - N'ajoute PAS au staging les fichiers contenant des secrets (
.env, identifiants, etc.) - Si
$ARGUMENTSest fourni, utilise-le comme message de commit - Si aucun argument, rédige un message de commit selon les conventions de CLAUDE.md :
- Utilise un préfixe de type :
feat:(nouvelle fonctionnalité) oufix:(correction de bug) - Mets l'accent sur le « pourquoi » plutôt que le « quoi »
- Termine par
Co-Authored-By: Claude
- Utilise un préfixe de type :
- Utilise un HEREDOC pour le message de commit afin d'assurer un formatage correct
4. Push
- Push avec le suivi de la branche amont :
git push -u origin HEAD
5. Création de la PR
- Utilise
gh pr createavec :- Un titre court (moins de 70 caractères)
- Un corps contenant
## Résumé(1 à 3 puces) et## Plan de test - Utilise un HEREDOC pour le corps
- Retourne l'URL de la PR à l'utilisateur
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.
- 12d ago First seen · 45 lines · 90 tokens per session scan A 9cc74caa3081
livre is a skill published in the GitHub repository naiersaidane/claude-mastery (51 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 634 once invoked, about $0.0005 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 skills, from other repositories
git-workflow
Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.
git-workflow
A Git workflow guide for organizing commits, branches, pull requests, releases, and automated version-control tasks. Git is the system developers use to track code changes and collaborate.
git-workflow
Helps with git workflows including conventional commit messages, branching strategies, merge conflict resolution, and changelog generation. Triggers on: "git commit message", "branching strategy", "resolve conflict", "generate changelog".
changelog
Use when writing a changelog or release notes. Covers what belongs in one, writing for users rather than for git, semantic versioning, and documenting breaking changes so nobody is surprised.
git-workflow
Use for branching, committing, history repair, and release hygiene. Covers atomic commits, rebase versus merge, bisect, reflog recovery, and undoing mistakes safely.
git
Granular git operations with conventional commits - stage, commit, push, PR, merge. Auto-splits commits by type/scope, blocks on secrets, delegates verbose work to git-manager subagent. GitHub CLI conventions: --body-file for PR bodies, treat gh pr checks exit 8 (pending) as retry not failure, guard run-id assignment…