run-task
Skill4 starsChanged 33 days agoMITView on GitHub
Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task <task>. Uses get_task, update_task, create_task_comment.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- krzysztof-wojtowicz/coffer-demotheir own version, first seen Nov 8, 2026
- jcarlosrodicio/normatheir own version, first seen Oct 9, 2026
- zahardev/aicontexttheir own version, first seen Apr 22, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- zahardev/aicontext★ 2same name
- jcarlosrodicio/norma★ 1same name
- krzysztof-wojtowicz/coffer-demo★ 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.
- backlog-groomingSkill
- daily-standupSkill
- getting-startedSkill
- orchestrateSkill
- project-planSkill
- refine-taskSkill
- review-workSkill
- run-workSkill
- triageSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
44 rules. 0 are common, 20 are distinctive, and 24 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
20
Distinctive
This author's own choices. Worth a look.
24
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Keep changes tightly scoped to the requested outcome within the task scope.
- Very specific: line 34
If a task slug/id is provided, load it with get_task.
- Very specific: line 40
Follow the shared AgiFlow project-management guidelines in references/agiflow-agents.md — agent assignment, the task status workflow and …
- Very specific: line 60
Use list_tasks MCP tool to show available tasks:
- Distinctive: line 62
Do NOT pick up tasks in "Planning" status — they have not been groomed yet
- Distinctive: line 64
Ask user to select which task to work on.
- Distinctive: line 79
If task status is "Planning": REFUSE to execute
- Very specific: line 85
If task status is "Todo", use update_task MCP tool to set status to "In Progress".
- Distinctive: line 86
Create a TODO list of acceptance criteria in execution order (use TodoWrite tool).
- Very specific: line 87
Document execution start in task via update_task devInfo:
- Very specific: line 99
BEFORE editing any code: Use vibe-lint MCP get-file-design-pattern (MANDATORY)
- Very specific: line 101
AFTER editing code: Use vibe-lint MCP review-code-change (MANDATORY)
- Very specific: line 102
Update task devInfo with implementation notes:
- Distinctive: line 112
Update your TODO list (mark criterion as completed)
- Distinctive: line 115
Commit changes with meaningful commit messages
- Distinctive: line 116
Run tests to ensure no regressions
- Distinctive: line 117
Update task devInfo with progress
- Distinctive: line 121
When ALL acceptance criteria are met:
- Distinctive: line 122
Verify all criteria have status checked
- Very specific: line 123
Use update_task to move status to "Testing"
- Distinctive: line 124
Run the full test suite for affected code:
- Distinctive: line 130
Update devInfo with passing test results
- Very specific: line 142
If retryCount >= maxRetries (default maxRetries = 2):
- Very specific: line 143
Use update_task to move status to "Blocked"
- Very specific: line 144
Use create_task_comment to document the repeated failure and what human intervention is needed
- Distinctive: line 145
Stop — do not retry
- Very specific: line 147
Use update_task to move status back to "Todo"
- Very specific: line 148
Use create_task_comment to document the failure reason
- Distinctive: line 149
Stop — agent will re-pick from Todo queue on next cycle
- Distinctive: line 153
After tests pass, review all files changed (use git diff).
- Very specific: line 163
Use update_task to set status to "Review" and save draft PR text and commit message:
- Very specific: line 182
Note on draftCommitMessage: Write a conventional commit message that will be used for the final git commit.
- Very specific: line 184
Use create_task_comment to add final summary:
- Very specific: line 186
All files created/modified (use file.ts:42 format)
- Distinctive: line 187
Test coverage and results
- Distinctive: line 192
If blocked at any point:
- Very specific: line 193
Use update_task to set status to "Blocked"
- Very specific: line 194
Use update_task to update devInfo with blocker details:
- Very specific: line 202
Use create_task_comment on task with blocker information explaining what human intervention is needed
- Very specific: line 206
Use get_task to review task details before starting
- Very specific: line 207
Use list_task_comments to see previous progress updates
- Very specific: line 208
Use update_task to track devInfo and acceptance criteria progress
- Distinctive: line 212
vibe-lint MCP: ALWAYS use before/after editing files for pattern compliance
- Distinctive: line 213
Scaffolding MCP: Document scaffolded code in task comments
“Common” is measured: kept by at least 6 in 10 of the 3 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
Invoked as
/agiflow:run-task. In hosts without slash-prompts, this skill is triggered by matching intent and drives AgiFlow via its MCP tools.
Usage:
/agiflow:run-task <task-slug-or-id>- Execute specific task/agiflow:run-task- List and select from available tasks
Examples:
/agiflow:run-task DXX-2(using slug)/agiflow:run-task 01K8FABMNEJG1XTA9JGHSNFV40(using ID)/agiflow:run-task(interactive selection)
Guardrails
- Favor straightforward, minimal implementations first and add complexity only when it is requested or clearly required.
- Keep changes tightly scoped to the requested outcome within the task scope.
- A task represents a single, focused unit of work that can be completed in one session.
If a task slug/id is provided, load it with get_task; otherwise list available tasks with list_tasks for selection.
AgiFlow Project Management Guidelines
Follow the shared AgiFlow project-management guidelines in references/agiflow-agents.md — agent assignment, the task status workflow and transitions, work-unit best practices, and the tags strategy apply to this workflow.
Task Status Workflow
Tasks move through these statuses in order:
Planning → Todo → In Progress → Testing → Review → Done
Exception paths: Blocked (requires human intervention), Cancelled (terminal).
IMPORTANT: Planning Status Guard
This skill ONLY executes tasks in "Todo" or later status. Tasks in "Planning" have NOT been groomed and are NOT ready for execution. Use backlog-grooming to promote Planning tasks to Todo first.
Steps Track these steps as TODOs and complete them one by one.
1. Task Selection & Loading
If task slug/id NOT provided:
- Use
list_tasksMCP tool to show available tasks:- For the ready queue, filter by
status: "Todo"(sorted by priority automatically) - Do NOT pick up tasks in "Planning" status — they have not been groomed yet
- Display: slug, title, priority, assignee, acceptance criteria count
- For the ready queue, filter by
- Ask user to select which task to work on.
- Once user selects, proceed with the selected task slug/id.
If task slug/id IS provided: 4. Use get_task MCP tool with the provided slug/id to retrieve:
- Task: title, description, priority, status, acceptance criteria
- Comments: Previous progress updates and discussions
- Review the task details to understand:
- Complete requirements and deliverables
- Acceptance criteria that must be met
- Any blockers or dependencies noted in comments
5b. PLANNING STATUS GUARD (MANDATORY):
- If task status is "Planning": REFUSE to execute
- Report: "Cannot execute task [SLUG]: still in Planning status. Use backlog-grooming to promote it to Todo first."
- STOP execution — do not proceed
2. Start Task Execution
- If task status is "Todo", use
update_taskMCP tool to set status to "In Progress". - Create a TODO list of acceptance criteria in execution order (use TodoWrite tool).
- Document execution start in task via
update_taskdevInfo:devInfo: { currentSession: "<current-session-id>", startedAt: "<timestamp>" }
3. Implement Task
- For each acceptance criterion:
- Review the specific requirement
- BEFORE editing any code: Use
vibe-lintMCPget-file-design-pattern(MANDATORY) - Implement the criterion keeping changes minimal and focused
- AFTER editing code: Use
vibe-lintMCPreview-code-change(MANDATORY) - Update task
devInfowith implementation notes:devInfo: { filesChanged: ["path/to/file.ts:42"], testResults: { passed: true, coverage: "85%" }, notes: "Implementation notes here", currentSession: "<session-id>" } - Mark acceptance criterion as checked via
update_task - Update your TODO list (mark criterion as completed)
- Between acceptance criteria:
- Commit changes with meaningful commit messages
- Run tests to ensure no regressions
- Update task devInfo with progress
4. Testing Phase
- When ALL acceptance criteria are met:
- Verify all criteria have status checked
- Use
update_taskto move status to "Testing" - Run the full test suite for affected code:
- Unit tests
- Integration tests
- Type checking and lint
- If tests PASS:
- Update devInfo with passing test results
- Proceed to step 13 (Task Completion)
- If tests FAIL:
- Increment
retryCountin devInfo:devInfo: { ...existing, retryCount: (existing.retryCount ?? 0) + 1, lastFailureReason: "<description of what failed>" } - If
retryCount >= maxRetries(default maxRetries = 2):- Use
update_taskto move status to "Blocked" - Use
create_task_commentto document the repeated failure and what human intervention is needed - Stop — do not retry
- Use
- If
retryCount < maxRetries:- Use
update_taskto move status back to "Todo" - Use
create_task_commentto document the failure reason - Stop — agent will re-pick from Todo queue on next cycle
- Use
- Increment
5. Task Completion
- After tests pass, review all files changed (use git diff).
- Draft a PR description for the task (DO NOT create the PR yet - just draft the text):
- Title format:
[TASK-SLUG] Task title(e.g.,[DXX-2] Add user authentication) - Body should include:
- Task reference and summary
- List of changes made
- Files modified (use
file.ts:42format) - Test results
- Title format:
Use
update_taskto set status to "Review" and save draft PR text and commit message:{ status: "Review", devInfo: { ...existing, draftCommitMessage: "feat(auth): add user authentication\n\n- Add login endpoint with session management\n- Add password validation\n- Add unit tests for auth flow", draftPr: { title: "[DXX-2] Add user authentication", body: "## Summary\n\nImplemented user authentication feature.\n\n## Changes\n\n- Added login endpoint\n- Added session management\n\n## Files Modified\n\n- src/auth/login.ts:42\n- src/auth/session.ts:15\n\n## Test Results\n\nAll tests passing." }, finalNotes: "All acceptance criteria met. Files changed: [...]. Tests passing.", completedBy: "<member-id>", totalDuration: "45 minutes" } }Note on draftCommitMessage: Write a conventional commit message that will be used for the final git commit. Format:
type(scope): descriptionwith optional body listing changes.- Use
create_task_commentto add final summary:- Task scope and goals achieved
- All files created/modified (use
file.ts:42format) - Test coverage and results
- Any follow-up work needed
6. Handle Blockers
- If blocked at any point:
- Use
update_taskto set status to "Blocked" - Use
update_taskto update devInfo with blocker details:devInfo: { ...existing, blockedReason: "<why the task is blocked>", blockedBy: "<memberId or 'system'>" } - Use
create_task_commenton task with blocker information explaining what human intervention is needed
- Use
Reference
- Use
get_taskto review task details before starting - Use
list_task_commentsto see previous progress updates - Use
update_taskto track devInfo and acceptance criteria progress
Integration with Other Tools
- vibe-lint MCP: ALWAYS use before/after editing files for pattern compliance
- Scaffolding MCP: Document scaffolded code in task comments
Common Mistakes to Avoid
- ❌ Starting work without reviewing task details with
get_task - ❌ Not moving task to "In Progress" before starting
- ❌ Skipping vibe-lint MCP validation (MANDATORY for every file)
- ❌ Not tracking devInfo (files changed, tests, session ID)
- ❌ Marking acceptance criteria checked before actually completing them
- ❌ Moving to "Review" without going through "Testing" first
- ❌ Not documenting progress in comments
- ❌ Forgetting to add file references (file.ts:42 format) in final comment
- ❌ Not running tests before moving to "Review"
- ❌ Not committing changes incrementally
- ❌ Moving to "Blocked" without explaining what human intervention is needed
- ❌ Skipping retryCount increment when moving failed task back to "Todo"
- ❌ Starting work on a task in "Planning" status (must be promoted to "Todo" via
backlog-groomingfirst)
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.

