agentleFS
Sign inStart free
AnastasiyaWAnastasiyaW/codex-claude-code-config/skills/plan-to-tickets/SKILL.md

plan-to-tickets

Skill213 starsChanged 3 days agoMITView on GitHub

Use when a large plan, PRD, feature, refactor, research plan, or multi-step coding task must be split into small ready-for-agent tickets with acceptance criteria, verification commands, blockers, and vertical tracer-bullet slices. Do not use for small tasks that should be implemented directly, single-bug fixes, or chat-only summaries.

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no issue tracker is explicitly selected, write local tickets under:

    line 12
  2. Distinctive:

    Prefer vertical tracer bullets: a narrow complete path through the required layers, not "all backend" then "all UI" then "all tests".

    line 40
  3. Distinctive:

    Put prefactoring first only when it makes a later slice smaller or safer.

    line 42
  4. Very specific:

    Keep dependencies explicit in ## Blocked By.

    line 43
  5. Distinctive:

    Do not include stale-prone file paths unless the path is already a stable contract or current codebase evidence.

    line 44
  6. Distinctive:

    Do not publish external tracker issues unless the user asked for that tracker.

    line 45
  7. Distinctive:

    Read the plan/spec and current repo context needed to avoid fake tickets.

    line 49
  8. Distinctive:

    Do not use this to postpone work.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan To Tickets

Turn a large plan into small, independently executable tickets. Use this before handing a broad plan to agents, before long autonomous work, or when the user asks for tickets/issues/slices.

Output Location

If no issue tracker is explicitly selected, write local tickets under:

<project>/.agent/tickets/<YYYY-MM-DD>-<slug>/

Each ticket is one Markdown file:

TICKET-001-short-slug.md

Required Ticket Shape

Each ticket must include these headings exactly:

  • ## Status
  • ## Parent
  • ## What To Build
  • ## Acceptance Criteria
  • ## Verification
  • ## Blocked By
  • ## Notes

## Status must contain ready-for-agent only when all acceptance criteria and verification steps are concrete.

## Acceptance Criteria must contain checklist items (- [ ] ...).

## Verification must contain at least one command, script, test, artifact check, or explicit manual-review gate.

Slicing Rules

  • Prefer vertical tracer bullets: a narrow complete path through the required layers, not "all backend" then "all UI" then "all tests".
  • A ticket must be independently verifiable.
  • Put prefactoring first only when it makes a later slice smaller or safer.
  • Keep dependencies explicit in ## Blocked By; write None when it can start immediately.
  • Do not include stale-prone file paths unless the path is already a stable contract or current codebase evidence.
  • Do not publish external tracker issues unless the user asked for that tracker.

Workflow

  1. Read the plan/spec and current repo context needed to avoid fake tickets.
  2. Draft ticket files in dependency order.
  3. Run the validator:
python "$env:USERPROFILE\.claude\claude-code-config\scripts\validate_agent_tickets.py" --tickets-dir <ticket-dir>
  1. Fix every validator failure before claiming the ticket split is ready.
  2. Report the ticket directory and the count of ready tickets.

Gotchas

  • Horizontal tickets overload later agents. If a ticket cannot be verified alone, split it differently.
  • "Implement feature" is not an acceptance criterion. ACs must describe observable behavior or artifacts.
  • "Run tests" alone is weak verification. Name the test command or the artifact that proves success.
  • Do not use this to postpone work. Ticketization is for large plans; small tasks should be implemented directly.

Download now (ZIP)

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.

Check your setup, free