Skip to content
Agentmart
Submit a tool

undominated-announced-not-safe

Refuse a safety claim built from none-announced, unknown, or unrated.

Skill by Undominated.ai

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying undominated-announced-not-safe?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/lenvanderhof-undominated-announced-not-safe

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

Refuse a safety claim built from none-announced, unknown, or unrated. Those labels do not establish that a subject is safe.

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
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/undominated-announced-not-safe

What's inside

Skill name
undominated-announced-not-safe
Description
Refuse a safety claim built from none-announced, unknown, or unrated. Those labels do not establish that a subject is safe.
License
MIT
Metadata
author: Undominated.ai · version: 1.0.0
Instructions
35 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (7)

  • LICENSE
  • SKILL.md
  • called-safe.json · examples/
  • called-unsafe.json · examples/
  • other-label.json · examples/
  • synthetic.json · examples/
  • check.py · scripts/

SKILL.md (first lines)

# A missing announcement is not safe

Use when a safety sentence is about to treat a missing announcement as a favourable verdict.

1. The only labels this checker reads are `none-announced`, `unknown`, and `unrated`. Any other label is invalid here.
2. `claimedSafe` true is a review. The result never sets `established` to true.
3. `claimedSafe` false or null can pass, and `established` stays false. A denial is not rewritten into a safety verdict, and a null is not a verdict either.
4. No source is fetched. The label you supply is the whole input.

## Input contract

`label` is one of the three words above. `claimedSafe` is true, false, or null. A string and the JSON number 1 are invalid.

## Deliverable and limits

Return the label, the claim you supplied, and `established: false`. A pass does not certify safety. It records that this label was not promoted to safe.

`examples/synthetic.json` passes with `none-announced` and a null claim. The true-claim example requires review.

## Run the local check

Resolve paths relative to this skill directory:

```sh
python3 scripts/check.py examples/synthetic.json
python3 scripts/check.py /absolute/path/to/your-input.json
```

The examples are **synthetic**, not a safety evaluation. Python 3.10+; standard library only. The script reads one explicit UTF-8 JSON file, prints JSON and makes no network requests or file writes.

Exit codes: `0` consistency check passed, `1` review required, `2` invalid input. CLI argument and malformed-input errors return structured JSON; `--help` displays usage text. Unknown or duplicate JSON fields, non-JSON constants and invalid types are rejected. Files are limited to 1 MiB.

This source-only skill is **not included in undominated-check@0.4.0**. Keep `SKILL.md`, the checker, examples and MIT licence together. A pass validates the bounded supplied-input contract, not production suitability or permission to publish. The skill does not authorize external actions.

From Lenvanderhof/Undominated.ai, MIT.

More from Lenvanderhof/Undominated.ai

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 7, 2026 (22 days ago)
Last release
Oct 9, 2026 (21 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Undominated.ai

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get undominated-announced-not-safe running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying undominated-announced-not-safe?

CallGet help
Cite this page

undominated-announced-not-safe skill. Agent Mart. https://agentmart.dev/skills/lenvanderhof-undominated-announced-not-safe (last updated 2026-10-24)