agent-loop
Skill31 starsChanged 7 days agoMITView on GitHub
Orchestrates a multi-agent loop involving planning, development, review, and publishing sub-agents to implement and publish features test-first and with high standards compliance.
- Commits and pushes
We split this skill into the rules it gives an agent
9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
6
Distinctive
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
- Distinctive: line 46
Verify compile checks and execution results.
- Very specific: line 47
Update the status of the task in tasks/todo.md to completed [x].
- Very specific: line 58
Check tasks/todo.md for the next incomplete task.
- Distinctive: line 59
If tasks remain, loop back to Step 2.
- Distinctive: line 60
If all tasks are completed, proceed to Step 4.
- Distinctive: line 65
Verify git status and stage all changed files.
- Distinctive: line 66
Commit files using the Conventional Commits syntax and push to origin.
- Very specific: line 71
All tasks in tasks/todo.md are marked [x].
- Distinctive: line 73
All unit and integration tests in the test suite pass successfully.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Multi-Agent Iteration Loop
This skill coordinates four independent agents (planning, development, review, and publisher) in a continuous loop to deliver and publish spec-compliant, standard-abiding features.
graph TD
Start["User Request / Spec"] --> Plan["1. Planning Subagent"]
Plan --> SavePlan["Generate tasks/plan.md & todo.md"]
SavePlan --> ApprPlan{"User Approval?"}
ApprPlan -- No --> Plan
ApprPlan -- Yes --> Dev["2. Development Subagent"]
Dev --> ImpTask["Implement Next Task via TDD"]
ImpTask --> Rev["3. Review Subagent"]
Rev --> Check{"Any Findings?"}
Check -- Yes (Bug / Smell) --> Dev
Check -- No --> CheckMore{"More Tasks?"}
CheckMore -- Yes --> Dev
CheckMore -- No --> Pub["4. Publisher Subagent"]
Pub --> OpenPR["Create Branch, Commit & gh pr create"]
OpenPR --> Done["Done - Pull Request Published"]Workflow Execution Steps
[!IMPORTANT] Coordinator Constraint: The coordinator agent executing this skill MUST NOT write implementation code, create source files, or modify files in the codebase directly during the development phase. The coordinator is solely responsible for planning, orchestrating the loop, conducting code reviews, and managing publishing. All code changes and task implementations MUST be delegated to the spawned subagents.
1. Planning Phase
- Spawn the
planningsubagent to read the user request/specification and codebase structure. - The
planningagent will outputtasks/plan.md(architecture, design, tasks) andtasks/todo.md(checkbox todo list). - Once the plan is saved, present it to the user for feedback and approval.
2. Development Phase (Task Implementation)
- Select the first incomplete task from
tasks/todo.md. - Spawn the
developmentsubagent to implement that task. - The
developmentagent must:- Operate incrementally, writing a failing unit test first.
- Implement only enough code to pass the test.
- Verify compile checks and execution results.
- Update the status of the task in
tasks/todo.mdto completed[x].
3. Review Phase (Quality Gates)
- Spawn the
reviewsubagent to perform standard and spec audits on the branch's git diff. - The
reviewagent outputs findings under## Standardsand## Specheaders. - Evaluate results:
- If there are findings (e.g., hard violations or baseline smells):
- Send a message to the
developmentsubagent containing the reviewer's report. - Instruct the developer to resolve the bugs or smells.
- Rerun the
reviewagent once the developer has updated the branch.
- Send a message to the
- If there are 0 findings:
- Check
tasks/todo.mdfor the next incomplete task. - If tasks remain, loop back to Step 2.
- If all tasks are completed, proceed to Step 4.
- Check
- If there are findings (e.g., hard violations or baseline smells):
4. Publishing Phase (Deployment Gate)
- Spawn the
publishersubagent to automate the integration and deployment lifecycle. - The
publisheragent must:- Verify
git statusand stage all changed files. - Commit files using the Conventional Commits syntax and push to origin.
- Execute
gh pr createwith standard metadata titles/descriptions to open the GitHub Pull Request. - Return the direct URL link to the Pull Request.
- Verify
Exit Criteria
- All tasks in
tasks/todo.mdare marked[x]. - The
reviewagent reports 0 standard violations or spec omissions. - All unit and integration tests in the test suite pass successfully.
- The
publisheragent has successfully pushed and opened a GitHub Pull Request, sharing its URL.
Sub-Agent Skill References
To ensure execution consistency, each sub-agent in this loop is dedicated to executing a specific workspace skill. They must load and re-use the following guides:
- Planning Sub-Agent:
- Primary Skill: planning-and-task-breakdown (used to analyze dependencies, partition slices, and output plans).
- Development Sub-Agent:
- Primary Skill: test-driven-development (drives test-first RED-GREEN loops at public boundaries).
- Review Sub-Agent:
- Primary Skill: code-review (performs two-axis checks for standard compliance and specification compliance).
- Publisher Sub-Agent:
- Primary Skill: pull-request (automates git checkout, commits, pushes, and GitHub CLI PR creation).
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- joelhooks/joelclaw★ 66same name
- 2lab-ai/llmux★ 8same name
- leolin310148/tmact★ 4same name
- SiluPanda/codex-agent-loop★ 4same name
- nadavnaveh/skills★ 2same name
- Artithea/agent-loop★ 0same name
- edenbuilds/agentloop★ 0same name
- jaron-goh-centr/claude-skills★ 0same name
- Yuuqq/know-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 repository9 other files it gives its agents.
- codebase-context-generatorSkill
- code-reviewSkill
- manual-automationSkill
- planning-and-task-breakdownSkill
- project-change-intelligenceSkill
- pull-requestSkill
- slack-cliSkill
- test-driven-developmentSkill
- yt-random-comment-pickerSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

