goal-test SKILL.md skillA

goal-test from restarter/lets-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add restarter/lets-workflow/goal-test@git:20260525.c780b5a

Pins git:20260525.c780b5a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
restarter/lets-workflow
Path
.claude/skills/goal-test/SKILL.md
Versions recorded
3
Latest version
git:20260525.c780b5a, committed May 25, 2026
First version recorded
May 25, 2026
Size
24,266 bytes
Repository stars
17
License
MIT

Local sandbox for experimenting with Claude Code's /goal command (stop-hook condition + LLM-evaluator driving autonomous work toward a verifiable end state) applied to LETS workflows. Use when the user says "goal test", "goal-test", "test the goal skill", "stop hook experiment", "автономна задача", "long-running goal", or wants to design a /goal contract that chains /lets:* commands (plan → execute → check → commit → done) toward a defined termination. Local-only — not part of the lets plugin…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# goal-test (local experiment)

`/goal` installs a **session-scoped Stop hook with an LLM-evaluated termination condition**. After every model turn, an evaluator-LLM reads the transcript and judges whether the goal is met. If not, the turn is rejected and the model must keep working. Best fit: convergent autonomous work (drive a task / epic / PR to a defined end state).

**Not for periodic polling** — that's `/loop`'s job (see `loop-test` skill).

## How `/goal` actually works

Sources: `claude` binary v2.1.150 strings + official docs ([code.claude.com/docs/en/goal](https://code.claude.com/docs/en/goal)) + community write-ups (see References).

### Mechanics

1. User runs `/goal <condition>`. Stored as session-scoped state. **Cap: 4000 characters** per condition.
2. After every model turn (assistant message that would normally yield), evaluator-LLM is invoked with the condition + transcript.
   - **Evaluator runs on your configured "small fast model"** (Haiku by default). Eval tokens are billed separately; Anthropic describes them as "typically negligible" but they accumulate on long runs.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add restarter/lets-workflow/goal-test@sha256:cda95a72bb68f866

The line at the top of this page pins the label git:20260525.c780b5a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4hf44f2vpqyzwtgf.svg)](https://markdownregistry.com/a/art_4hf44f2vpqyzwtgf)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, all committed on May 25, 2026.

versioncommittedcommitsizeaudit
git:20260525.c780b5a latest2026-05-25 c780b5a 24,266 BA view · diff
git:20260525.fd0bda82026-05-25 fd0bda8 23,121 BA view · diff
git:20260525.1fa826e2026-05-25 1fa826e 21,325 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (24266 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

restarter/lets-workflow · 17 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4hf44f2vpqyzwtgf
GET https://markdownregistry.com/api/v1/resolve?ref=restarter/lets-workflow/goal-test
GET https://markdownregistry.com/api/v1/blob/cda95a72bb68f866f81c1436f4c6e99fb7c64169419cd8856b62aea7e6f17ce7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from restarter/lets-workflow

goal-plan-clean SKILL.md skill
restarter/lets-workflow · .claude/skills/goal-plan-clean/SKILL.md · Compose a /goal that drives a plan-review-fix loop autonomously. Use when the user says "clean my plan"…
git:20260526.73d26de · audit A · 17 stars
loop-bb-pr SKILL.md skill
restarter/lets-workflow · .claude/skills/loop-bb-pr/SKILL.md · Compose a /loop that monitors a Bitbucket PR for activity (new comments, review state changes, merge, decline) via the…
git:20260526.73d26de · audit A · 17 stars
loop-gh-pr SKILL.md skill
restarter/lets-workflow · .claude/skills/loop-gh-pr/SKILL.md · Compose a /loop that watches all open GitHub PRs for activity (new PRs, new commits, new comments) and auto-prepares a…
git:20260923.58e2441 · audit A · 17 stars
loop-test SKILL.md skill
restarter/lets-workflow · .claude/skills/loop-test/SKILL.md · Local sandbox for experimenting with Claude Code's /loop command (interval + dynamic/self-paced scheduling) applied to…
git:20260525.fd0bda8 · audit A · 17 stars
CLAUDE.md CLAUDE.md file
restarter/lets-workflow · CLAUDE.md
git:20261103.16c64f9 · audit A · 17 stars
actor-fetch-personality SKILL.md skill
restarter/lets-workflow · plugins/lets/skills/actor-fetch-personality/SKILL.md · Internal skill for commands. Fetch and validate personality from URL or file path for Actor agent. Do not trigger on…
git:20260517.62e185f · audit A · 17 stars
agent-report SKILL.md skill
restarter/lets-workflow · plugins/lets/skills/agent-report/SKILL.md · Internal skill for commands. The file transport for agent reports - hand every Task-dispatched agent a REPORT_FILE…
git:20261103.16c64f9 · audit A · 17 stars
apply-fixes SKILL.md skill
restarter/lets-workflow · plugins/lets/skills/apply-fixes/SKILL.md · Internal skill for commands. Apply a review's verified fixes to the working tree when nothing needs deciding - the…
git:20261103.16c64f9 · audit A · 17 stars
artifact-path SKILL.md skill
restarter/lets-workflow · plugins/lets/skills/artifact-path/SKILL.md · Internal skill for commands. Resolve a unique, task-scoped, collision-safe path for an artifact written under .lets/…
git:20261013.1de4c10 · audit A · 17 stars
backlog-workflow SKILL.md skill
restarter/lets-workflow · plugins/lets/skills/backlog-workflow/SKILL.md · Dynamic Workflow asset for /lets:backlog review --workflow. Not auto-triggered - a workflow script invoked via…
git:20260802.f9b266b · audit A · 17 stars
commit SKILL.md skill
restarter/lets-workflow · plugins/lets/skills/commit/SKILL.md · This skill should be used when committing code changes - "commit", "git commit", "закоміть", "зроби коміт"…
git:20261015.158a674 · audit A · 17 stars
create-task SKILL.md skill
restarter/lets-workflow · plugins/lets/skills/create-task/SKILL.md · This skill should be used when creating a task in the active tracker - "create task", "create issue", "bd create", "new…
git:20261014.d0bd237 · audit A · 17 stars

Every file in restarter/lets-workflow

Other files named goal-test

goal-test SKILL.md skill
undefined-ui/second-brain-os · plugins/agents-course/skills/goal-test/SKILL.md · Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally…
git:20261007.c7fa35b · audit A · 1,499 stars

Browse by kind, by grade A, or by owner.