Rapport d’audit du skill
Token Diet Rapport d’audit.
Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.
Trust Score OpenAgentSkill
Trust Score OpenAgentSkill
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
Adoption GitHub
Info76
556 stars GitHub
Activité stars/forks
Avertissement60
556 stars et 3 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Maintenance récente
Validé88
2 mois depuis le dernier push
Clarté de licence
Avertissement42
Inconnu
Complétude README/SKILL.md
Validé90
Les métadonnées incluent suffisamment de contexte d’usage et de workflow
Risque dépendances/runtime
Avertissement54
command execution surface, credential or environment access
Disponibilité de l’installation
Validé92
npx skills add Kulaxyz/token-diet
Sécurité de la commande d’installation
Info68
credential-bearing install command, standard package or runtime install path
Surface de permissions
Échoué36
secrets or environment access, shell or command execution
Preuve du dépôt
Validé86
https://github.com/Kulaxyz/token-diet
État de revue
Validé88
Données de revue IA disponibles
Résultats prouvés par Agent
Info54
Pas encore de données de résultats Agent
Vérifications
Revue d’installation et d’adoption
Chemin d’installation
92
npx skills add Kulaxyz/token-diet
Dépôt
88
https://github.com/Kulaxyz/token-diet
Licence
45
Inconnu
Maintenance
88
2 mois depuis le dernier push
Revue IA
88
Approved with no listed issues
Complétude README/SKILL.md
90
Usable description available
Risque de dépendances
54
command execution surface, credential or environment access
Sécurité de la commande d’installation
68
credential-bearing install command, standard package or runtime install path
Surface de permissions
36
secrets or environment access, shell or command execution
Activité stars/forks
60
556 stars et 3 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Adoption
88
556 stars GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Avertissements
- La licence est ambiguë
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Stars/forks activity: 556 stars, 3 forks; issue activity unavailable in current metadata
- License clarity: Unknown
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
Méthode
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Comparer les options proches
Skills associés à auditer ensuite
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
169K Stars · Rapport d’audit
Grill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
165K Stars · Rapport d’audit
To Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
165K Stars · Rapport d’audit