clean-and-true

clean-and-true is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 112 tokens per session (382 once invoked), scanned A, original, Apache-2.0.

A cleanup pass for newly edited project files that checks for stale wording, unnecessary padding, confusing prose, unsupported claims, and duplicated facts.

In plain words
What is it for?
Use it after changing durable documentation or other project artifacts to route the result through the relevant cleanup checks.
Why use it?
It catches avoidable problems before a finished change is handed back, especially details that could confuse someone reading the result later.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the odin plugin — 29 skills, 14 plugins shipped together

Good fit Use it after changing durable documentation or other project artifacts to route the result through the relevant cleanup checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/clean-and-true
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 OutlineDriven/odin-claude-plugin --skill clean-and-true
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin, the plugin that ships this one along with the rest of its 29 skills, 14 plugins.

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 clean-and-true

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/clean-and-true/github.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/clean-and-true)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/clean-and-true"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/clean-and-true/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 clean-and-true

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/clean-and-true"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/clean-and-true.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 382 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00112 $0.00382
Opus 5 $0.00056 $0.00191
Sonnet 5 $0.00022 $0.00076
Haiku 4.5 $0.00011 $0.00038

Measured 10d ago against content hash 77cf4c6859d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

clean-and-true 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 10d 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.

skills/clean-and-true/SKILL.md · 30 lines

What it actually says

Clean and true

Taste your own cooking right after you make it, routing to whichever hygiene skills the change earned.

Method

After creating or changing a durable artifact and before handing it off, route to what applies:

What changed Route to When to skip
Drifted prose that reads as sediment rewrite-clean-v0 No sediment accumulated
Padded prose whose every rule still binds debloat Nothing padded to cut
Anything a stranger must understand alone shower Short-lived or author-only
A reality-grounded claim verify-both-ways No such claim
A truth duplicated across places consolidate-to-one-home Single home already holds
Voice, tells, or stack residue in prose unslop Not prose, or not stale

Degrades gracefully: use the skills present and skip the rest. debloat and reorder are recommendations here, not calls.

Apply the findings in this session, then serve it.

Completion

Every routed skill was run or had a stated reason for being skipped. Findings were applied or consciously deferred with a reason. A pass that finds nothing to genuinely improve changes nothing.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 30 lines · 112 tokens per session scan A 77cf4c6859d5

Subscribe to this mod's changes

clean-and-true is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 112 tokens to every session and 382 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens