codex-think-about
1
总安装量
1
周安装量
#77587
全站排名
安装命令
npx skills add https://github.com/lploc94/codex_skill --skill codex-think-about
Agent 安装分布
amp
1
cline
1
opencode
1
cursor
1
continue
1
kimi-cli
1
Skill 文档
Codex Think About
Purpose
Use this skill for peer reasoning, not code review. Claude and Codex are equal thinkers.
Prerequisites
- A clear question or decision topic from the user.
codexCLI installed and authenticated.codex-reviewskill pack is installed (npx github:lploc94/codex_skill).
Runner
RUNNER="{{RUNNER_PATH}}"
Workflow
- Ask user to choose reasoning effort level:
low,medium,high, orxhigh(default:high). Gather factual context only (no premature opinion). SetEFFORTto their choice. - Build round-1 prompt from
references/prompts.md. - Start Codex thread with
node "$RUNNER" start --working-dir "$PWD" --effort "$EFFORT". - Poll with adaptive intervals (Round 1: 60s/60s/30s/15s…, Round 2+: 30s/15s…). After each poll, report specific activities from poll output (e.g. which files Codex is reading, what topic it is analyzing). See
references/workflow.mdfor parsing guide. NEVER report generic “Codex is running” â always extract concrete details. - Claude responds with agree/disagree points and new perspectives.
- Resume via
--thread-idand loop until consensus or stalemate. - Present user-facing synthesis with agreements, disagreements, and confidence.
Effort Level Guide
| Level | Depth | Best for |
|---|---|---|
low |
Surface check | Quick sanity check |
medium |
Standard review | Most day-to-day work |
high |
Deep analysis | Important features |
xhigh |
Exhaustive | Critical/security-sensitive |
Required References
- Execution loop:
references/workflow.md - Prompt templates:
references/prompts.md - Output contract:
references/output-format.md
Rules
- Keep roles as peers; no reviewer/implementer framing.
- Separate facts from opinions.
- Detect stalemate when arguments repeat with no new evidence.
- End with clear recommendations and open questions.