Agent
Role — The final, aggregating gate before a change is declared "done".
22 yesterday A 0 tokens
original Apache-2.0
Agent
Role — Failure-path and resilience reviewer for async flows, SSE, retries, and idempotency.
22 yesterday A 0 tokens
original Apache-2.0
Agent
Role — Cross-cutting security lens for every change.
22 yesterday A 0 tokens
original Apache-2.0
Agent
Role — Owner of the testing mandate: TDD, coverage, DTO fuzzing, and QA scripts.
22 yesterday A 0 tokens
original Apache-2.0
Skill Claude CodeCodex
Use when the user explicitly requests the complete AI-Psychiatry framework through one all-in-one command that evaluates and orchestrates every available skill until the task is proven complete.
3 17d ago A 40 tokens
original MIT
anti-gaming
30Skill Claude CodeCodex
Use when commands, labels, agents, counters, or classifications change while the same underlying behavior continues.
3 17d ago A 24 tokens
original MIT
Skill Claude CodeCodex
Use when analysis paralysis, speculative branching, repeated replanning, premature architecture work, or indecision blocks a reversible implementation or test.
3 17d ago A 30 tokens
original MIT
Skill Claude CodeCodex
Use when objective switching, novelty chasing, repeated context switching, optional branches, or ADHD-like distraction as a behavioral analogy interrupts delivery.
3 17d ago A 29 tokens
original MIT
Skill Claude CodeCodex
Use when BLOCKED is proposed after difficulty, uncertainty, unfamiliar code, a slow operation, or a small number of failed attempts.
3 17d ago A 30 tokens
copy · 91% MIT
Skill Claude CodeCodex
Use when debugging, architecture inspection, research, or repository exploration risks becoming open-ended, recursive, speculative, or disconnected from a decision.
3 17d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Use when DONE is proposed with unrun tests, missing requirements, inferred success, happy-path-only proof, or unresolved required findings.
3 17d ago A 30 tokens
copy · 91% MIT
Skill Claude CodeCodex
Use when requested behavior appears complete, remaining work is optional, perfectionism delays delivery, or the agent continues auditing, refining, testing, or researching after proof.
3 17d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Use when context is overloaded or compression may have removed requirements, constraints, evidence, blockers, or decisions.
3 17d ago A 25 tokens
copy · 84% MIT
Skill Claude CodeCodex
Use when a long session, large tool output, repeated discussion, or handoff needs a compact state that preserves decisions and enables continuation.
3 17d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Use when active context is large, stale, contradictory, repeatedly reread, or no longer represents current source and task state.
3 17d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Use when choosing which repository instructions, architecture, domain knowledge, files, tests, or deep guidance to load for a task without reading everything.
3 17d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Use when reviewers or judges repeat rounds, invent requirements, block on style, expand scope, or continue after correctness, security, regression, and explicit requirements are satisfied.
3 17d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Use when no productive next action can be selected because dependencies, authority, contradictory constraints, missing access, or unresolved evidence block progress.
3 17d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Use when an important implementation, architecture, security, data, or delivery decision rests on unresolved critical unknowns.
3 17d ago A 26 tokens
copy · 88% MIT
Skill Claude CodeCodex
Use when answers, progress updates, explanations, or questions risk verbosity, repetition, indirect wording, vague conclusions, or conversational loops.
3 17d ago A 30 tokens
original MIT
Skill Claude CodeCodex
Use when mandatory behavior, integration, security, migration, or data requirements lack the appropriate kind of proof.
3 17d ago A 25 tokens
copy · 84% MIT
Skill Claude CodeCodex
Use when files, services, commands, tests, APIs, configuration, architecture, publication, or runtime results are assumed without an authoritative repository or tool source.
3 17d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Use when a task needs explicit control of objective, scope, priority, nesting, retries, verification, progress, drift, recovery, or termination.
3 17d ago A 33 tokens
original MIT
Skill Claude CodeCodex
Use when an AI-Psychiatry budget expires while new evidence shows a narrow extension is required for correctness, security, or completion.
3 17d ago A 32 tokens
copy · 86% MIT