Goal Test

What it does

When your agent uses it

• The user wants to run an agent in a loop
• Asks how to know when an agent task is finished
• Says a goal like improve X needs to become checkable
• Building eval suites over many cases — that is evals-bootstrap

Example prompts

• “improve X”
• “/goal-test”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Extract the claim. Ask what the user wants true at the end, then
2. 2Prefer checks that already exist. The test suite, the linter, the
3. 3Write goal-test.sh (or .py if the checks are easier there) in the
4. 4Run it now. It should fail before the work is done — a goal test that
5. 5Offer the loop. If the user wants the agent driven until done, wrap it

What it can do on your machine

Read from SKILL.md and the folder at commit c7fa35b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • claude
  • make

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • secondbrainos.dev

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Goal Test loads about 754 tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 326 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~104

When it runs · the whole SKILL.md, loaded when a task matches

~754

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from undefined-ui/second-brain-os at commit c7fa35b, republished under its MIT licence (© undefined-ui). 326 words, ~754 tokens.

name

goal-test

description

Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap.

#!/usr/bin/env bash
# goal-loop.sh — run a headless agent until the goal test passes or attempts run out.
set -u
MAX_ATTEMPTS=5
for i in $(seq 1 "$MAX_ATTEMPTS"); do
  FEEDBACK=$(./goal-test.sh 2>&1) && { echo "done in $i attempt(s)"; exit 0; }
  claude -p "Goal: <the goal>. The goal test currently fails with:
$FEEDBACK
Fix the code so the goal test passes." \
    --permission-mode acceptEdits --output-format json > ".attempt-$i.json"
done
echo "goal test still failing after $MAX_ATTEMPTS attempts — falling back to a human"
exit 1

© undefined-ui, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/agents-course/skills/goal-test of undefined-ui/second-brain-os.

Open the folder on GitHubat commit c7fa35b

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in undefined-ui/second-brain-os, which our catalogue first saw on October 7, 2026.

• majiayu000/claude-skill-registryskills/bash/goal-test