coagent8-loop
Skill2 starsChanged 11 days agoMITView on GitHub
Carry out a non-trivial change in a loop led by you, with CoAgent8 for plan review and independent code review - requirements, plan, plan review, implementation, your own checks, independent review and fixes. Use when the user asks for a careful or reviewed implementation, a plan review before coding, or names the CoAgent8 loop. Not for trivial edits.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- coagent8-workflowSkill
- pr-mergeSkill
- coagent8-consultSkill
- coagent8-delegateSkill
- coagent8-doctorSkill
- coagent8-issueSkill
- coagent8-reviewSkill
- coagent8-sessionSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Recon: Read the relevant code and the project's documents.
- Distinctive: line 17
Requirements: Ask the user only about decisions that change the outcome.
- Distinctive: line 18
Plan: Write the objective, scope (files), observable acceptance criteria and the commands that prove them.
- Very specific: line 21
Plan review: Use coagent8-consult with task_type: implementation or architecture, the plan as proposal and the relevant paths in …
- Distinctive: line 29
Verify: Run the proof commands yourself and record each command, exit code and result.
- Very specific: line 32
Independent review: Use coagent8-review without the plan review's session, with a scope that covers the change and instructions holding the …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
CoAgent8 loop
You lead the loop and own every change: you make it yourself or delegate it. CoAgent8 consult and review agents run read-only; a delegate agent edits the workspace for you, and you check what it changed. This skill grants no permission. Commit, push, merge, deploy and publish only with the user's authority.
- Size. For a trivial edit skip the loop and make the change directly.
- Recon. Read the relevant code and the project's documents. List your assumptions and where each comes from.
- Requirements. Ask the user only about decisions that change the outcome.
- Plan. Write the objective, scope (files), observable acceptance criteria and the commands that prove them. Use the project's existing plan document if it has one; do not create plan files the user did not ask for.
- Plan review. Use
coagent8-consultwithtask_type: implementationorarchitecture, the plan asproposaland the relevant paths incontext_files. Continue the samesession_handlefor revisions. Give every finding a disposition: accepted, rejected with the reason, or deferred. After three rounds without agreement, show the open points to the user. - Implement once the user agrees with the plan, yourself or, for a
well-defined part, through
coagent8-delegatewith the plan's scope and proof commands. A delegated change is still yours to verify and review. - Verify. Run the proof commands yourself and record each command, exit code and result. Fix failures, at most two rounds, then report what still fails.
- Independent review. Use
coagent8-reviewwithout the plan review's session, with a scope that covers the change andinstructionsholding the acceptance criteria and the checks you ran. Fix accepted findings and review again with the review'ssession_handle, at most two more rounds. A code change invalidates the previous verdict. - Report the plan, finding dispositions, the checks you observed, the final
server
Verdict:and the remaining risks.
BLOCKED is not approval, and exhausted rounds are reported as they are, never as
success. Leave backend and model unset unless the user named one or a price
limit.
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.

