Skill Claude CodeCodex
Use after a non-trivial, recurring, or expensive failure when a concise evidenced lesson could prevent future repeated investigation.
3 17d ago A 26 tokens
original MIT
Skill Claude CodeCodex
Use when status reports emphasize tools, files, commits, plans, tokens, or agents while requirements and evidence remain unchanged.
3 17d ago A 29 tokens
copy · 92% MIT
Skill Claude CodeCodex
Use when an agent-control framework needs adversarial testing for fake productivity, loops, recursion, evidence gaps, or vague wording.
3 17d ago A 29 tokens
copy · 88% MIT
goal-lock
52Skill Claude CodeCodex
Use when the requested outcome is unclear, silently changing, being reinterpreted by discoveries, or disconnected from the active implementation.
3 17d ago A 28 tokens
original MIT
handoff-task
53Skill Claude CodeCodex
Use when work moves to another agent, session, person, or environment and the recipient needs enough state to continue without a sprawling narrative.
3 17d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Use when nested work is renamed, moved across agents, promoted to top level, or hidden behind research, validation, review, and dependency labels.
3 17d ago A 35 tokens
copy · 89% MIT
Skill Claude CodeCodex
Use when non-trivial implementation starts before what exists, what changes, why, risks, and validation are sufficiently known.
3 17d ago A 28 tokens
copy · 84% MIT
Skill Claude CodeCodex
Use when repository architecture, rules, skills, commands, context routing, manifests, or generated AI knowledge change and dependent sources may become stale.
3 17d ago A 32 tokens
original MIT
Skill Claude CodeCodex
Use when activity is high but requirements, blockers, tests, and deliverables remain unchanged across repeated edit, search, test, review, or planning cycles.
3 17d ago A 37 tokens
original MIT
Skill Claude CodeCodex
Use when commands, searches, file reads, edits, tests, critics, plans, context reloads, or strategies repeat without new evidence or acceptance progress.
3 17d ago A 35 tokens
original MIT
Skill Claude CodeCodex
Use when rules appear satisfied while their intent is bypassed, counters reset, classifications change conveniently, or an AI-Psychiatry audit is requested.
3 17d ago A 36 tokens
copy · 89% MIT
Skill Claude CodeCodex
Use when deciding whether task discoveries, decisions, preferences, architecture, failures, or lessons deserve durable repository memory.
3 17d ago A 26 tokens
original MIT
Skill Claude CodeCodex
Use when durable memory may contain assumptions, stale facts, contradictions, duplicates, obsolete decisions, or temporary debugging state.
3 17d ago A 26 tokens
copy · 88% MIT
Skill Claude CodeCodex
Use when two or more agents work concurrently, delegation may recurse, responsibilities overlap, dependencies can deadlock, or a coordinator must preserve scope and termination.
3 17d ago A 35 tokens
original MIT
never-stop
63Skill Claude CodeCodex
Use when the user explicitly requests maximum autonomous execution, no unnecessary questions, persistent recovery, independent decision-making, and continuous work until the full Definition of Done is proven.
3 17d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Use when status is unclear, activity is high, completion estimates feel unreliable, or the agent may be mistaking reading, reasoning, tools, or churn for progress.
3 17d ago A 37 tokens
original MIT
Skill Claude CodeCodex
Use when a task may be underthinking, sufficiently reasoned, or overthinking and the correct next action is unclear.
3 17d ago A 29 tokens
copy · 84% MIT
Skill Claude CodeCodex
Use when packages, services, ownership boundaries, entrypoints, tests, commands, or dependencies changed and the compact repository map needs a focused update.
3 17d ago A 33 tokens
original MIT
resume-task
67Skill Claude CodeCodex
Use when continuing work from saved task state, a compacted session, a handoff, or a new agent without rereading the entire repository.
3 17d ago A 32 tokens
original MIT
Skill Claude CodeCodex
Use when debugging changes assertions, mocks, exceptions, or symptoms without explaining materially important failure behavior.
3 17d ago A 24 tokens
copy · 84% MIT
Skill Claude CodeCodex
Use when system, user, repository, domain, AI-Psychiatry, skill, memory, or task-state instructions appear incompatible.
3 17d ago A 33 tokens
copy · 80% MIT
scope-guard
70Skill Claude CodeCodex
Use when newly discovered work, technical debt, refactors, audits, optimizations, or reviewer suggestions threaten to expand the user-authorized task.
3 17d ago A 33 tokens
original MIT
Skill Claude CodeCodex
Use when adjacent work is called required without dependency proof, or inconvenient required work is marked optional.
3 17d ago A 27 tokens
copy · 92% MIT
Skill Claude CodeCodex
Use when different commands, tools, runners, plans, or agents repeat the same hypothesis and evidence target.
3 17d ago A 29 tokens
copy · 84% MIT