Rapport d’audit du skill
sequential-opus-orchestrator Rapport d’audit.
Sequential single-Opus backlog walk over the ELAI plan corpus. Triggers when the user says "resume the opus walk", "opus walk", "continue the backlog walk", or "start the opus backlog walk". One paid Opus orchestrates FREE workers (kimi-k2.7 reads, glm-5.2 implements) to drain .elai_cc plans; a deterministic dispatch budget stops the session at a unit boundary and a FRESH Opus resumes from walk-state + handoff. Never two Opus concurrent.
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
Échoué30
21 stars GitHub
Activité stars/forks
Échoué32
21 stars et 8 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Maintenance récente
Validé88
1 mois depuis le dernier push
Clarté de licence
Validé86
MIT
Complétude README/SKILL.md
Validé86
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 DITlieD/ELAI-archive --skill sequential-opus-orchestrator
Sécurité de la commande d’installation
Validé92
Chemin d’installation standard de package ou runtime
Surface de permissions
Échoué36
secrets or environment access, shell or command execution
Preuve du dépôt
Validé86
https://github.com/DITlieD/ELAI-archive/tree/main/.agents/skills/sequential-opus-orchestrator
État de revue
Info66
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 DITlieD/ELAI-archive --skill sequential-opus-orchestrator
Dépôt
88
https://github.com/DITlieD/ELAI-archive/tree/main/.agents/skills/sequential-opus-orchestrator
Licence
86
MIT
Maintenance
88
1 mois depuis le dernier push
Revue IA
55
The skill is highly project-specific and depends on many external files (walk_state.py, .Codex/rules/*, prompts, etc.) that are not included in the skill directory, making it non-self-contained and hard to adopt outside the ELAI repository.
Complétude README/SKILL.md
86
Usable description available
Risque de dépendances
54
command execution surface, credential or environment access
Sécurité de la commande d’installation
92
Chemin d’installation standard de package ou runtime
Surface de permissions
36
secrets or environment access, shell or command execution
Activité stars/forks
32
21 stars et 8 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Adoption
42
21 stars GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Avertissements
- 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
- The skill is highly project-specific and depends on many external files (walk_state.py, .Codex/rules/*, prompts, etc.) that are not included in the skill directory, making it non-self-contained and hard to adopt outside the ELAI repository.
- Hardcoded Windows path 'F:\.ELAI_workflow' and WSL-specific commands reduce portability across environments.
- The skill references a 'harness Agent tool' that cannot route glm/kimi, implying a dependency on a specific harness implementation not described in SKILL.md.
- Low GitHub adoption signal
- 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
- GitHub adoption: 21 GitHub stars
- Stars/forks activity: 21 stars, 8 forks; issue activity unavailable in current metadata
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