Instructions file CodexOpenCode
Instructions for bikeread/promethos, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
Instructions file
Instructions for bikeread/promethos, covering claude.md, what this is, validation (the only "test" gate), skill taxonomy and skill file contract.
Instructions file Gemini CLI
Instructions for bikeread/promethos, a project described as: A skills-first framework for agent-system design, governance, evaluation, and evolution across domains.
Skill Claude CodeCodex
Use when an agent needs the smallest useful eval pack to catch regressions or false confidence early.
Skill Claude CodeCodex
Use when an agent's job is clear and you need to choose structure, boundaries, or single-agent vs multi-agent.
Skill Claude CodeCodex
Use proactively when an agent repeats a failure, loops, or degrades and needs a local root-cause check before redesign.
Skill Claude CodeCodex
Use when an agent idea is still fuzzy and v1 scope, success bar, or operating boundaries are not concrete.
Skill Claude CodeCodex
Use when an agent reads too much, misses key files, or needs a clear eager-vs-deferred context plan.
Skill Claude CodeCodex
Use when deciding what an agent should remember across turns or sessions versus fetch on demand.
Skill Claude CodeCodex
Use after autonomy policy is set and you need permission classes, defaults, approvals, and denial behavior.
Skill Claude CodeCodex
Use when a tool is misused or underspecified because its inputs, errors, or side effects are unclear.
Skill Claude CodeCodex
Use when the skill library feels crowded, redundant, stale, or mis-scoped and needs pruning or reshaping.
Skill Claude CodeCodex
Use when delegation is already justified and you need safe subagent ownership, context, and merge boundaries.
Skill Claude CodeCodex
Use when architecture is settled and you need an ordered implementation plan with checkpoints and verification.
Skill Claude CodeCodex
Use proactively when a user is defining, constraining, debugging, or evaluating an agent system and needs the right PromethOS skill.
Skill Claude CodeCodex
Use proactively when an agent lacks checkpoint policy or risky actions need clear human-review boundaries.
Skill Claude CodeCodex
Use proactively when a plan, skill, or agent keeps absorbing side quests and needs to return to core scope.
Skill Claude CodeCodex
Use after a failure, correction, or standout success to decide what reusable guardrail, eval, skill, or rule should follow.
Skill Claude CodeCodex
Use proactively before declaring success, shipping, or moving on when an agent or change needs fresh verification evidence.