Skip to content
Agentmart
Submit a tool

goal-post

Turn an outcome into a machine-checkable goal contract with actor, verifier, stop conditions, evidence, and human gates.

Skill by itsAR-VR

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/itsar-vr-goal-post

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Turn an outcome into a machine-checkable goal contract with actor, verifier, stop conditions, evidence, and human gates. Use before autonomous or multi-step execution.

Use cases: documents

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/goal-post

What's inside

Skill name
goal-post
Description
Turn an outcome into a machine-checkable goal contract with actor, verifier, stop conditions, evidence, and human gates. Use before autonomous or multi-step execution.
License
MIT
Instructions
16 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Goal Post

Write a compact goal contract containing:

- **Outcome:** the observable end state
- **Scope:** allowed systems, files, and non-goals
- **Actor:** who or what performs the work
- **Verifier:** an independent check that does not trust the actor's claim
- **Evidence:** exact tests, readbacks, artifacts, or live surfaces required
- **Stop conditions:** success, unsafe state, repeated failure, budget, and time limits
- **Human gates:** sends, publishing, payments, credentials, production changes, and destructive actions
- **Ledger:** attempts, results, and remaining blockers

The verifier must test the outcome, not the actor's explanation. A loop without an independent verifier and explicit stop conditions is not ready to run.

From itsAR-VR/public-skills, MIT.

More from itsAR-VR/public-skills

Signals

Stars
0
Forks
1
Open issues
1
Last commit (this folder)
Jul 14, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/itsAR-VR/public-skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from itsAR-VR

Cite this page

goal-post skill. Agent Mart. https://agentmart.dev/skills/itsar-vr-goal-post (last updated 2026-10-24)