agentleFS
Sign inStart free
ch4570ch4570/vulpora/skills/codex-agent-runtime/SKILL.md

codex-agent-runtime

Skill1 starsChanged 56 days agoApache-2.0View on GitHub

Record the fail-closed compatibility status of legacy Vulpora catalog-agent execution. This installable negative-contract skill must not run agents, discovery probes, or delegated tasks.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Call no tools. Do not run a runner script, discovery probe, native subagent, shell command, web request, MCP call, or delegated task.

    line 13
  2. Distinctive:

    If this source skill is invoked directly, return:

    line 20
  3. Distinctive:

    Use the host's normal reviewed coding workflow for the user's actual task.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Codex Agent Runtime — Unsupported

This is an installable negative-contract compatibility skill. It documents that the removed legacy runner must stay disabled even though this SKILL.md and its inert compatibility script can be discovered.

Call no tools. Do not run a runner script, discovery probe, native subagent, shell command, web request, MCP call, or delegated task. Do not search plugin caches, source checkouts, project paths, user paths, receipts, or environment variables for an executable copy.

Installing this skill copies only its own skill directory and receipt entry. It does not authorize agent execution or create an execution trust root.

If this source skill is invoked directly, return:

AGENT_RUNTIME_ERROR:project_execution_disabled

Use the host's normal reviewed coding workflow for the user's actual task. Do not present repository catalog metadata as installed, discovered, or executable runtime state.

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