plan-runner

Plugin plan-runner in MisterVitoPro/plan-runner. Commands read from the repo's manifest — 1 month ago.

Skills (2)

• pr

  Internal plan-runner step (invoked by the run skill at pipeline end, not run directly): push the run-owned integration branch and open or update a proper pull request -- conventional title, rich structured body (task outcomes, whole-branch diff, bug counts, stats), and a smart draft/ready default ba

• run

  Run a free-form Markdown implementation plan as a dependency-ready task DAG. Each cycle: analyze the plan into a task graph, run every ready task in its own disposable Git worktree (at most 6 at once), gate it with deterministic checks and an independent verifier, integrate verified commits onto a r

Subagents (6)

• plan-aggregator

  plan-runner pipeline agent that reads all per-task bug JSONs from a pipeline run, deduplicates and ranks bugs (P0-P3), produces a human-readable bugs.md summary, and generates a free-form Markdown fix-plan.md that is valid input for a re-run of the Plan Runner run skill.

• plan-analyzer

  plan-runner pipeline agent that reads a free-form Markdown implementation plan and returns a structured task graph: stable task IDs, explicit dependency edges, file ownership, TDD roles, and verification scope for dependency-ready DAG scheduling.

• plan-dev

  plan-runner pipeline agent that implements a single task from a task graph. Generic template -- the orchestrator parameterizes each invocation with the specific task title, excerpt, owned files, acceptance criteria, and Context7 flag.

• plan-integrator

  plan-runner central-integration protocol and conflict adjudicator. Defines how a task commit's ownership, stale base, deterministic-check evidence, and independent verdict are validated before it is serially applied to the run-owned integration branch.

• plan-test-author

  plan-runner pipeline agent that writes ONLY the failing tests for one testable task from a task graph. It never writes implementation -- a downstream impl agent makes the tests pass. Returns the test files and test IDs it added.

• plan-verifier

  plan-runner pipeline agent that independently verifies ONE task attempt against its acceptance criteria. Reads the task's committed work in its own worktree, the ownership evidence, and the gate logs; flags every gap as a structured bug entry.

Hooks (1)

• SessionStart

  node -e "const fs=require('fs');try{const p='.gitignore',e='**/plan-runner/';if(fs.existsSync(p)){const c=fs.readFileSync(p,'utf8');if(!c.split(/\r?\n/).some(l=>l.trim()===e)){fs.appendFileSync(p,(c.l

Similar plugins