wrapper
Skill1 starsChanged 6 months agoMITView on GitHub
Wraps any other Claude Code skill you have installed and runs the opencouncil board review on top of its output. Activates when the user prefixes a skill call with "wrap" or sets wrapping as default. Part of v2.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
If consensus passes (8 of 10, zero hard vetoes), the output reaches you with a one-line summary.
- Distinctive: line 16
If consensus fails, the wrapper sends the board flags back to the wrapped skill as input and asks for a revision.
≈ “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
Wrapper mode (v2)
opencouncil's second mode. Instead of running its own employees, the wrapper intercepts the output of any other Claude Code skill you have installed and runs the board review gate on top of it. Your existing skill keeps its voice and behaviour. Only the quality gate is added.
How it works
- You invoke any skill you have installed, prefixed with
wrap. Example:wrap marketing-storyteller draft a Reels script. - The wrapped skill runs normally and produces its output.
- The board reads the output.
- If consensus passes (8 of 10, zero hard vetoes), the output reaches you with a one-line summary.
- If consensus fails, the wrapper sends the board flags back to the wrapped skill as input and asks for a revision. Up to 3 loops.
Why this matters
Most users already have a stack of Claude Code skills they like. Switching off them to use opencouncil is friction. Wrapper mode means you keep your existing tools and just add the quality gate on top.
Compatible skills
Any skill that:
- Produces a discrete text output (not a long-running session)
- Accepts revision feedback as input on re-invocation
- Runs inside Claude Code
This covers the vast majority of skills on the public catalogue.
Activation
Three ways:
# one-off wrap
wrap <skill-name> <args>
# set wrapping as default for a skill
opencouncil wrap-default <skill-name>
# unwrap (revert to plain skill behaviour)
opencouncil unwrap <skill-name>Status
v2 release: design complete, implementation in progress. Track at ROADMAP.md.
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.