From planning-with-files
Bridges the active plan file to Claude Code's /goal primitive by deriving a termination condition from task_plan.md and invoking /goal until the plan is complete.
How this command is triggered — by the user, by Claude, or both
Slash command
/planning-with-files:plan-goalThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
Bridge the active plan to Claude Code's `/goal` primitive.
Steps:
1. Resolve the active plan: prefer `${PLAN_ID}` env var, then `.planning/.active_plan`, then newest `.planning/<dir>/`, then legacy `./task_plan.md`.
2. Read the resolved `task_plan.md`.
3. Derive a goal condition from the plan content:
- Default: "all phases in task_plan.md report Status: complete and check-complete.sh reports ALL PHASES COMPLETE"
- If user passed an argument: use that as an additional clause (e.g., `/plan-goal until all tests pass`)
4. Issue Claude Code's `/goal <condition>` with the derived text.
5...Bridge the active plan to Claude Code's /goal primitive.
Steps:
${PLAN_ID} env var, then .planning/.active_plan, then newest .planning/<dir>/, then legacy ./task_plan.md.task_plan.md./plan-goal until all tests pass)/goal <condition> with the derived text./goal clear cancels.If task_plan.md does not exist, refuse and direct user to run /plan first.
Why this exists:
/goal runs the agent until a small fast model confirms the condition is met. It evaluates the transcript only, not files. By deriving the condition from the plan file, this command turns the file-based plan into a measurable termination criterion for /goal, so the loop terminates when the plan is actually done, not when the conversation looks done.
Notes:
/plan-goal does not replace /goal. It composes with it. Users can still run /goal "any text" directly./goal enforces by quoting only phase headers + acceptance criteria, not full task body./plan-loop for a "babysit until done" workflow: /plan-loop cadence + /plan-goal termination.npx claudepluginhub othmanadi/planning-with-files --plugin planning-with-files/implImplements coding plan from specified plan-file directory using persistent markdown files (task_plan.md, findings.md, progress.md) for state, progress, and rules enforcement.
/goalDefines complex goals with structured success criteria, tracks progress, validates completion objectively. Supports templates, status, clear, and history subcommands.
/implement_planImplements technical plans from a specified thoughts/shared/plans path, executing phases with verification, updating checkboxes, and pausing for manual review if needed.
/execute-from-deep-researchImplements approved technical plans from research-plans/plans/<plan-path>: reads context, executes phases, verifies success criteria, updates checkboxes.
/planupdateQuickly syncs plan file with current codebase state: checks task completions, updates statuses and paths without executing changes.
/loop-with-codex-reviewStarts an iterative development loop where Claude implements a plan, writes summaries, and receives Codex review feedback until completion or max iterations. Accepts plan path, max rounds, and codex model/timeout options.