tidybot-skill-publish

tidybot-skill-publish is a skill for Claude Code, Codex from TidyBot-Services/Tidybot-Universe. It costs 35 tokens per session (604 once invoked), scanned A, original, Apache-2.0.

A publishing workflow for moving a tested robot skill from a development folder into the tidybot-skills organization on GitHub. It covers the required files, testing threshold, repository creation, and catalogue update.

In plain words
What is it for?
Use it after explicit approval to rename a development skill, create its public repository, push the code, and add its description, dependencies, author, and test statistics to the organization catalogue.
Why use it?
It prevents an unfinished or insufficiently tested skill from being published and makes the release steps consistent.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it after explicit approval to rename a development skill, create its public repository, push the code, and add its description, dependencies, author, and test statistics to the organization catalogue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tidybot-services/tidybot-universe/tidybot-skill-publish
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add TidyBot-Services/Tidybot-Universe --skill tidybot-skill-publish
Clone the repo
git clone --depth 1 https://github.com/TidyBot-Services/Tidybot-Universe

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tidybot-skill-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/tidybot-services/tidybot-universe/tidybot-skill-publish/github.svg)](https://agentmods.dev/skills/tidybot-services/tidybot-universe/tidybot-skill-publish)
Your own site
<a href="https://agentmods.dev/skills/tidybot-services/tidybot-universe/tidybot-skill-publish"><img src="https://agentmods.dev/badge/skills/tidybot-services/tidybot-universe/tidybot-skill-publish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tidybot-skill-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/tidybot-services/tidybot-universe/tidybot-skill-publish"><img src="https://agentmods.dev/badge/skills/tidybot-services/tidybot-universe/tidybot-skill-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 604 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00604
Opus 5 $0.00017 $0.00302
Sonnet 5 $0.00007 $0.00121
Haiku 4.5 $0.00003 $0.00060

Measured 12d ago against content hash 5532c6443343, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tidybot-skill-publish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill-agent-setup/openclaw/workspace/skills/tidybot-skill-publish/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tidybot Skill Publishing

Only publish when the user explicitly approves. Ask first: "Want me to publish this so other Tidybots can use it?"

Prerequisites

  • Skill has dev-tb- prefix with proper OpenClaw structure (SKILL.md, scripts/main.py, scripts/deps.txt)
  • Skill has 70%+ cumulative success rate
  • Stats were not invalidated by recent code changes (any code change resets stats — re-test first)
  • GitHub CLI authenticated (gh auth login)

Publishing Steps

  1. Rename from dev-tb- to tb-: Move the skill folder from dev-tb-my-skill/ to tb-my-skill/.

  2. Create a repo in the tidybot-skills org. The repo name drops the tb- prefix (e.g. local tb-pick-up-object → remote tidybot-skills/pick-up-object):

    gh repo create tidybot-skills/<skill-name-without-tb-prefix> --public
    
  3. Push skill code to the new repo

  4. Update catalog.json in tidybot-skills/wishlist:

    {
      "<skill-name>": {
        "repo": "tidybot-skills/<skill-name>",
        "description": "What the skill does",
        "author": "<your-agent-name>",
        "dependencies": ["dep1", "dep2"],
        "success_rate": 0,
        "total_trials": 0,
        "institutions_tested": 0
      }
    }
    

    Set success_rate and total_trials to 0 — public stats start fresh.

  5. Update wishlist.json if this skill fulfills a wishlist item — set status to "done" and add the repo path

Catalog Fields

Field Description
repo GitHub repo path (tidybot-skills/<name>)
description What the skill does
author Agent or person who built it
dependencies List of skill repo names this depends on
success_rate Percentage of successful trials (0–100)
total_trials Total number of trial runs performed
institutions_tested Number of distinct labs that tested this

Wishlist Status Values

Status Meaning
pending Not started
building Agent working on it
done Available in catalog.json

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 65 lines · 35 tokens per session scan A 5532c6443343

Subscribe to this mod's changes

tidybot-skill-publish is a skill published in the GitHub repository TidyBot-Services/Tidybot-Universe (56 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 604 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.