agentleFS
Sign inStart free
moveju112moveju112/skill_verify/skills/crosscheck/SKILL.md

crosscheck

Skill1 starsChanged 38 days agoMITView on GitHub

Claude-hosted Claude↔Codex crosschecks of improvement ideas, plans, and completed changes. Automatically selects independent proposals, draft critique, or mutual review and allows candid rejection. Use for explicit requests such as "크로스체크", "코덱스랑 핑퐁", "둘이 의견 취합해", "cross-check with codex", or "/crosscheck". Discussing or editing this skill does not authorize another model call.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. slpy22/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every Codex call goes through this entrypoint's scripts/codex_ask.sh, which links to the shared implementation.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Claude-hosted Crosscheck

This compatibility entrypoint delegates to the shared procedure in verify. Read that file and follow its routing, permission, evidence, wrapper, strategy, stopping, and reporting contracts. Do not maintain a second workflow here.

  • Claude is the host; Codex is the read-only counterpart. The host owns implementation. In Codex, use the shared entrypoint's model-family routing instead.
  • Choose the strategy automatically, within task-scoped reviewer permission; do not ask which method to use. Respect an explicitly selected method.
  • Infer the stopping stage from intent: opinions → analyze, plans → plan, completed work → verify, authorized implementation → full. Advice does not default to implementation.
  • For advice and planning, read the shared strategy reference. Broad improvement exploration normally uses independent proposals plus mutual review; a concrete draft uses critique; a narrow exploration uses independent proposals.
  • Say when an idea is poor value, recommend keeping the current approach when justified, and preserve evidence-based dissent. No mandatory praise, criticism, or consensus.
  • Every Codex call goes through this entrypoint's scripts/codex_ask.sh, which links to the shared implementation. Keep its read-only sandbox and exact returned session ID; never call codex exec directly or recursively invoke crosschecking.
  • Preserve user model/effort settings. Local edits, Git changes, remote mutations, and deployment retain their existing approval boundaries.
  • Reply in the user's language. Report actual reviewer responses and checks only; no claimed crosscheck without a collected response.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free