acp-connect
Skill1 starsChanged 4 months agoMITView on GitHub
Connect Codex to ACP — identity & governance for shell commands, plus the self-optimization data plane
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Check if ~/.acp/credentials exists (already configured?)
- Very specific: line 10
If not: open https://cloud.agenticcontrolplane.com/plugin/authorize in the browser
- Distinctive: line 11
Wait for the user to paste their token
- Very specific: line 13
Verify by hitting GET https://api.agenticcontrolplane.com/govern/health
- Distinctive: line 17
Keep it conversational and seamless.
≈ “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.
Files
Help the user connect to the Agentic Control Plane.
- Check if
~/.acp/credentialsexists (already configured?) - If not: open
https://cloud.agenticcontrolplane.com/plugin/authorizein the browser - Wait for the user to paste their token
- Store the token in
~/.acp/credentialswithchmod 600 - Verify by hitting
GET https://api.agenticcontrolplane.com/govern/health - Remind them to trust the plugin's hooks (Codex skips plugin hooks until reviewed): they will be prompted, or can review under Codex's hooks settings
- Direct them to
https://cloud.agenticcontrolplane.com/logsto see their audit trail
Keep it conversational and seamless. The user should go from zero to seeing their first logged tool call in under 2 minutes.
After setup, let them know: "Every shell command I run is now logged to your ACP workspace, and your policies decide what needs approval. The ACP MCP tools (acp_cost, acp_audit, acp_optimize, …) also give me your workspace's cost and quality data, so you can ask things like 'what did my agents spend this week?'"
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.

