codex-solver
Skill9 starsChanged 6 months agoMITView on GitHub
Запускает Codex в режиме Triple Solution Finder: находит OBVIOUS (простой/проверенный), NON-OBVIOUS (неожиданный), и BEST (оптимальный) вариант решения любой задачи.
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-skepticSkill
- codex-tracySkill
- combinatorial-creativitySkill
- common-groundSkill
- conductorSkill
- consilienceSkill
- construct-measurement-gateSkill
- convertSkill
- The first 60 shown.
The file
Files
Codex Solver — Triple Solution Finder
Когда использовать
- Есть задача и непонятно как решать
- Нашёл одно решение — хочешь проверить есть ли лучше
- Архитектурный выбор — нужны альтернативы с трейдоффами
- Claude предложил подход — хочешь независимый второй взгляд
Как запустить
Скажи Claude: "запусти codex-solver на [задача/проблема]"
Claude выполнит:
/codex:rescue --wait "SOLVER MODE — Triple Solution Finder.
Problem: [описание задачи]
Context: [стек, ограничения, цели]
Find exactly THREE solutions:
━━━ SOLUTION 1: OBVIOUS ━━━
The boring, proven, "everyone does it this way" approach.
- No cleverness, no novelty
- Battle-tested in production
- Easy to understand and maintain
- What a senior engineer would suggest at 11pm on a Friday
━━━ SOLUTION 2: NON-OBVIOUS ━━━
The unexpected angle. What if we:
- Inverted the problem?
- Removed a constraint everyone assumes is fixed?
- Used a tool from a completely different domain?
- Did nothing (is the problem worth solving)?
Search the web for: how do top engineers approach [problem type] in 2026?
━━━ SOLUTION 3: BEST ━━━
Optimal balance of: correctness + maintainability + speed to implement + risk
May combine elements from above or be entirely different.
Output format:
## Solution 1 — OBVIOUS
[implementation approach]
Pros: | Cons: | Time: | Risk:
## Solution 2 — NON-OBVIOUS
[implementation approach]
Why unexpected: [what assumption it breaks]
Pros: | Cons: | Time: | Risk:
## Solution 3 — BEST (recommended)
[implementation approach]
Why best: [specific reasoning]
Pros: | Cons: | Time: | Risk:
## My pick: Solution [N]
[1-2 sentence justification]"Примеры использования
запусти codex-solver: нужно кэшировать результаты API вызовов в хуках
запусти codex-solver: как хранить состояние между сессиями без файлов
запусти codex-solver на проблему медленного wiki поиска в prompt_wiki_inject.pyИнтерпретация
- Если Solution 1 = Solution 3 → задача простая, не усложняй
- Если Solution 2 = Solution 3 → текущий подход устарел, стоит переосмыслить
- Если все три разные → архитектурный выбор, обсуди с командой
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.

