goal-setter-skill

agent
Security Audit
Pass
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 94 GitHub stars
Code Pass
  • Code scan — Scanned 10 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Shape rough requests into evidence-backed /goal completion contracts — an Agent Skill for Claude Code and Codex

README.md

goal-setter

Turn rough long-running work into a compact Codex /goal with a clear finish line.

goal-setter is a Codex skill for work that needs more than a one-off prompt. It
turns a rough request into a short goal that fixes the result, the evidence for
success, the boundaries, and the stop rules, while leaving implementation
judgment to the runner.

It favors verification targets over rule-heavy procedures: the goal should say
what must be proven, not prescribe every step.

Built for Codex. Works on Claude Code too.

日本語

Goal Setter icon: loose requests converging into a checked goal

When to Use It

Do not turn every request into a Goal. Use goal-setter when the work can keep
going across several checks and the finish line must be judged by evidence.

Work Better format
One clear edit, explanation, or review Normal prompt
Narrow work that may need a few tries One sentence or short paragraph Goal
Migration, performance work, broad bug fixing, or evidence-backed research Standard Goal
Long research or high-risk change Goal plus the smallest needed plan, checklist, or evaluation file

What It Does

  • Reconstructs the intended result before drafting.
  • Adds only clauses that change the result, evidence, boundary, risk, or stop
    decision.
  • Interviews one material question at a time when the request is too ambiguous
    for an honest Goal and each answer determines the next question; bundles
    independent blockers.
  • Keeps small work light; uses subagents when feedback loops, parallel
    exploration, context isolation, or independent verification can improve Done,
    and creates separate tasks only when the user explicitly asks for them.

Details live in docs/RUNTIME.md. Examples live in
docs/EXAMPLES.md.

Install

Pick one install path:

If you use Install Invoke with
Codex App /plugins Codex App Plugin $goal-setter:goal-setter ...
Codex local skills Codex Skill $goal-setter ...
Claude Code Claude Code marketplace /goal-setter:goal-setter ...
Another agent with Skills CLI support Skills CLI the agent's skill invocation syntax

Most Codex App users should install only the Codex App Plugin.

Codex App Plugin

In Codex, open /plugins, choose Add plugin marketplace, and enter:

Source: gotalab/goal-setter-skill
Git ref: main
Sparse paths: plugins/goal-setter

Then install Goal Setter from the Plugins screen.

Codex Skill

In Codex chat:

$skill-installer install https://github.com/gotalab/goal-setter-skill/tree/main/skills/goal-setter

Restart Codex, then invoke with $goal-setter.

Claude Code

/plugin marketplace add gotalab/goal-setter-skill
/plugin install goal-setter@goal-setter

Invoke with /goal-setter:goal-setter.

Skills CLI

npx skills add gotalab/goal-setter-skill

Usage

Draft a goal without activating it:

$goal-setter draft a goal for migrating our API client to v2

Shape and activate a goal:

$goal-setter set a goal: all checkout tests pass after the refactor

goal-setter sets the Goal through Codex's native Goal mechanism. When feedback
loops, parallel exploration, context isolation, or independent verification
could improve the Done decision, goal-setter actually spawns subagents; it does
not merely describe them as available. It does not force a fixed sequence of
roles or stages; the parent chooses the next useful shape from current evidence
and cost. If that delegation should continue across Goal turns, the Goal keeps
an outcome-level instruction to spawn subagents, wait for their evidence, and
synthesize it.
create_thread creates separate user-owned tasks, so it is used only when the
user explicitly requests separate tasks, threads, or worktrees.

Docs

Repository

skills/goal-setter/SKILL.md          # the skill
skills/goal-setter/scripts/          # goal length validator
scripts/                             # packaging and release checks
plugins/goal-setter/                 # Codex plugin bundle
.claude-plugin/                      # Claude Code plugin metadata

License

MIT

Reviews (0)

No results found