codex-skeptic
Skill9 starsChanged 6 months agoMITView on GitHub
Запускает Codex в режиме falsification-first: ломает идею/код/архитектуру ДО реализации. Ищет hidden assumptions, failure modes, edge cases. Возвращает confidence score и конкретные условия провала.
In this repository164 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- agents/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- claude-md/CLAUDE.mdCLAUDE.md
- hooks/CLAUDE.mdCLAUDE.md
- insight-architectSkill
- agent-teamsSkill
- brainstormingSkill
- claim-decomposerSkill
- context-engineeringSkill
- dispatcherSkill
- git-worktreesSkill
- hd-mavp-routerSkill
- mentor-modeSkill
- reference-registrySkill
- routing-policySkill
- skill-self-updateSkill
- tdd-workflowSkill
- ab-testSkill
- academic-researchSkill
- advanced-methodology-extensionsSkill
- agent-governanceSkill
- ai-hyp-gateSkill
- algorithm-designSkill
- analystSkill
- archcode-genomicsSkill
- arm-cortex-microcontrollersSkill
- atomizeSkill
- backward-traceabilitySkill
- boyko-constraint-engineSkill
- boyko-epistemic-auditSkill
- boyko-goal-expansion-100Skill
- boyko-knowledge-architectureSkill
- boyko-leverage-mapSkill
- boyko-methodSkill
- boyko-preflightSkill
- boyko-project-radarSkill
- boyko-rippleSkill
- boyko-scientific-consortiumSkill
- boyko-specialistSkill
- boyko-toolcheckSkill
- boyko-triangle-auditSkill
- boyko-why-ladderSkill
- browser-actSkill
- build-autoSkill
- c4-architectureSkill
- career-prepSkill
- changelog-genSkill
- citation-managementSkill
- code-debuggingSkill
- code-materialitySkill
- codex-solverSkill
- codex-tracySkill
- combinatorial-creativitySkill
- common-groundSkill
- conductorSkill
- consilienceSkill
- construct-measurement-gateSkill
- convertSkill
- The first 60 shown.
The file
Files
Codex Skeptic — Falsification Engine
Когда использовать
- Перед реализацией новой фичи — проверить идею
- После написания кода — найти что сломается
- Архитектурное решение — оспорить assumptions
- Когда Claude одобрил, но есть сомнения
Как запустить
Скажи Claude: "запусти codex-skeptic на [идея/файл/архитектура]"
Claude выполнит:
/codex:rescue --wait "SKEPTIC MODE — falsification-first analysis.
Target: [описание цели]
Your mission: BREAK THIS before it costs time or money.
Step 1 — List every hidden assumption (min 5)
Step 2 — For each assumption: what happens if it's wrong?
Step 3 — Find the single most likely failure mode
Step 4 — Find the non-obvious failure mode (the one no one checks)
Step 5 — Search web for: has this approach failed before? why?
Output format:
## Confidence Score: X/10
## Hidden Assumptions: [list]
## Most Likely Failure: [specific scenario]
## Non-Obvious Failure: [the one everyone misses]
## Verdict: SHIP / FIX FIRST / ABANDON
## If FIX FIRST: exactly what to fix (1-3 items max)"Примеры использования
запусти codex-skeptic на hooks/moc_autolink.py
запусти codex-skeptic на идею добавить Redis кэш
запусти codex-skeptic на архитектуру async_wrapper паттернаИнтерпретация результата
| Score | Значение |
| 8-10 | Шипи — Codex не нашёл серьёзных проблем |
| 5-7 | Исправь сначала — есть реальные риски |
| 0-4 | Стоп — фундаментальная проблема |
Связка со скептик-агентом Claude
Для максимального эффекта: сначала /skeptic (Claude red-team), потом codex-skeptic — два независимых взгляда с разными моделями.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.