recursive-improve: Skill for Claude Code

.agents/skills/ratchet/SKILL.md

ratchet is a skill for Claude Code, Codex from kayba-ai/recursive-improve. It costs 0 tokens per session (11 once invoked), scanned A, original, Apache-2.0.

A skill whose contents are stored in a RATCHET_SKILL.md file.

In plain words
What is it for?
The input only identifies the referenced file, so its concrete jobs are not known.
Why use it?
The available description is too thin to identify the problem it addresses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is kayba-ai/recursive-improve's own configuration. It tells Claude Code and Codex how to work on recursive-improve itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything recursive-improve configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kayba-ai/recursive-improve. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kayba-ai/recursive-improve/main/.agents/skills/ratchet/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kayba-ai/recursive-improve

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 ratchet

README.md
[![agentmods](https://agentmods.dev/badge/skills/kayba-ai/recursive-improve/ratchet.svg)](https://agentmods.dev/skills/kayba-ai/recursive-improve/ratchet)
Your own site
<a href="https://agentmods.dev/skills/kayba-ai/recursive-improve/ratchet"><img src="https://agentmods.dev/badge/skills/kayba-ai/recursive-improve/ratchet.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11 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 $0.00000 $0.00011
Opus 5 $0.00000 $0.00005
Sonnet 5 $0.00000 $0.00002
Haiku 4.5 $0.00000 $0.00001

Measured 8d ago against content hash d110d5f9d698, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ratchet 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 8d 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.

.agents/skills/ratchet/SKILL.md · 1 lines

What it actually says

../../../recursive_improve/data/RATCHET_SKILL.md

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. 8d ago First seen · 1 lines · 0 tokens per session scan A d110d5f9d698

Subscribe to this mod's changes

ratchet is a skill published in the GitHub repository kayba-ai/recursive-improve (253 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 11 tokens. 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.

Related

Other skills, from other repositories

creator

Create, improve, and review AgentUse agent files. Use when authoring .agentuse agents, designing agent workflows, configuring frontmatter, adding MCP servers, subagents, schedules, approval gates, skills, or choosing project structure and automation patterns.

agentuse/agentuse · 52 tokens

deep-research

Orchestrate autonomous deep web research, parallel scraping, citation synthesis, fact checking, and persistent memory using the Deep Research MCP server. Use when asked to 'deep research', 'research this topic', 'fact check claim', 'compare sources', or perform comprehensive multi-source investigation with zero API…

SECRET4422/mcp-deep-research-server · 64 tokens

tester

Test and validate AgentUse agents without real side effects. Use when verifying a new or changed .agentuse file, dry-running an agent, testing approval-gate flows unattended, mocking tool outputs, or iterating on an agent in a closed loop before letting it run for real.

agentuse/agentuse · 58 tokens

runner

Run and manage AgentUse agents from the CLI. Use when you need to list agents, run an agent, inspect sessions, start or inspect the AgentUse server, work with schedules, or understand runtime command behavior.

agentuse/agentuse · 45 tokens

onboarding

Guide a new AgentUse user from a confirmed project to one validated first agent and its first CLI or Web UI run. Use for terminal setup and Create my first agent handoffs.

agentuse/agentuse · 39 tokens

core

Core AgentUse usage guide. Read this before running AgentUse commands. Covers the builtin skill catalog, installed skill inspection, agent discovery, running agents, creating agents, sessions, server usage, schedules, and when to load specialized AgentUse builtin skills.

agentuse/agentuse · 52 tokens