Individual skill

goal-prep

Goal Prep for GoalBuddy. Use for broad, long-running, stalled, vague, detailed, planned, or unhealthy Codex or Claude Code work that needs a structured /goal intake, autonomous task discovery, role-tagged Scout/Judge/Worker delegation, one active task, durable receipts, and a PM-owned rolling board that maximizes the chance of a successful goal run.

goalbuddy/SKILL.md

Read pinned source

Source commit e9823cc64cf1473c78e879831e955d53161ca5d1

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 825
Repository last updated: Oct 2, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 24,449 bytes
SKILL.mdcore · 24,449 bytes
agents/README.mddoc · 1,082 bytes
agents/config-snippet.tomlasset · 131 bytes
agents/goal_judge.tomlasset · 3,008 bytes
agents/goal_scout.tomlasset · 1,776 bytes
agents/goal_worker.tomlasset · 3,088 bytes
agents/openai.yamlasset · 653 bytes
references/goal-execution.mddoc · 24,233 bytes
scripts/apply-receipt.mjsruns · 9,205 bytes
scripts/check-can-stop.mjsruns · 2,676 bytes
scripts/check-goal-state.mjsruns · 26,140 bytes
scripts/check-update.mjsruns · 4,011 bytes
scripts/dispatch-task.mjsruns · 11,257 bytes
scripts/install-agents.mjsruns · 1,178 bytes
scripts/parallel-plan.mjsruns · 6,432 bytes
scripts/render-task-prompt.mjsruns · 14,194 bytes
surfaces/local-goal-board/README.mddoc · 3,215 bytes
surfaces/local-goal-board/assets/goalbuddy-mark.pngasset · 1,198,990 bytes
surfaces/local-goal-board/examples/sample-goal/.gitignoreasset · 18 bytes
surfaces/local-goal-board/examples/sample-goal/notes/T001-scout.mddoc · 94 bytes
surfaces/local-goal-board/examples/sample-goal/state.yamlasset · 3,415 bytes
surfaces/local-goal-board/examples/subgoal-parent/goal.mddoc · 95 bytes
surfaces/local-goal-board/examples/subgoal-parent/notes/.gitkeepasset · 1 bytes
surfaces/local-goal-board/examples/subgoal-parent/state.yamlasset · 1,488 bytes
surfaces/local-goal-board/examples/subgoal-parent/subgoals/T004-board-view/goal.mddoc · 77 bytes
surfaces/local-goal-board/examples/subgoal-parent/subgoals/T004-board-view/notes/.gitkeepasset · 1 bytes
surfaces/local-goal-board/examples/subgoal-parent/subgoals/T004-board-view/state.yamlasset · 1,258 bytes
surfaces/local-goal-board/scripts/lib/goal-board.mjsruns · 71,275 bytes
surfaces/local-goal-board/scripts/local-goal-board.mjsruns · 21,375 bytes
surfaces/local-goal-board/test/local-goal-board.test.mjsruns · 37,841 bytes
templates/agents.mddoc · 1,805 bytes
templates/goal-prompt.txtdoc · 105 bytes
templates/goal.mddoc · 6,386 bytes
templates/note.mddoc · 379 bytes
templates/state.yamlasset · 5,405 bytes

Read excerpt


# Goal Prep

`$goal-prep` (Codex) or `/goal-prep` (Claude Code) prepares a GoalBuddy board. It does not start execution automatically, but the board and harness-specific starter command must be shaped so the next run continues into safe execution by default.

GoalBuddy is for autonomous, long-running Codex or Claude Code work where the PM thread may need to discover the work, define tasks, sequence them, delegate them, execute them, verify them, and keep going without the human decomposing every step.

The loop is:

```text
raw user intent -> intake compiler -> goal oracle -> local work surface -> one active task -> receipt -> proof loop -> repeat
```

GoalBuddy's core invariant is: