universal-invariant-baseline

universal-invariant-baseline is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 47 tokens per session (837 once invoked), scanned A, original, Apache-2.0.

A workflow for applying invariant-first rules to a named local implementation. An invariant is a condition that must always remain true.

In plain words
What is it for?
Use it to refine a specified source file or module so its correctness conditions are checked consistently.
Why use it?
It exposes invalid states early and reduces special-case handling in the target code.

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-code plugin — 60 skills shipped together

Good fit Use it to refine a specified source file or module so its correctness conditions are checked consistently.

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

Made for: Claude Code, Codex.

Or install odin-code, the plugin that ships this one along with the rest of its 60 skills.

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 universal-invariant-baseline

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/universal-invariant-baseline"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/universal-invariant-baseline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 837 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 $0.00047 $0.00837
Opus 5 $0.00023 $0.00418
Sonnet 5 $0.00009 $0.00167
Haiku 4.5 $0.00005 $0.00084

Measured 4d ago against content hash 8d880dd6a961, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

universal-invariant-baseline 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 4d 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.

plugins/odin-code/skills/universal-invariant-baseline/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal invariant baseline

Contract

Field Bound contract
Trigger User explicitly requests an invariant-first, fail-fast, special-case-eliminating baseline for a named implementation.
Authority Reversible local: writes only the named local artifact; rollback is version control (restore) or undo (file deletion). No remote mutation.
Side effect Replace the target local file with its invariant-first, fail-fast, special-case-eliminating refinement.
Done All named invariant checks pass and no unresolved special-case artifacts remain.

Inputs

Required:

  • TARGET: path to the local source file or module to baseline.
  • LANGUAGE: the target's language (e.g., python, rust, typescript). Required to select correct invariant patterns.

Procedure

  1. Validate the request. Confirm TARGET is a concrete, scoped implementation task with a named local path. If TARGET is absent, empty, or points to a non-local artifact, raise BLOCKED-INPUT and stop. Done when: TARGET is confirmed as a concrete local path.
  2. Enumerate invariants. For LANGUAGE, enumerate the language-native invariant patterns that govern correctness: type contracts, ownership/borrow rules, null/void guards, resource lifecycle ordering, and domain-specific preconditions. Write each as a named, executable check with a unique identifier. Done when: every invariant pattern is a named, executable check with a unique identifier.
  3. Insert fail-fast guards. Before every mutable state operation, every external call, and every branching decision, insert the matching invariant check. If any check fails, halt immediately with INVARIANT-FAIL: <identifier> and the observed violation. The target artifact is unchanged until all checks pass. Done when: every mutable state operation, external call, and branching decision has a matching invariant guard.
  4. Eliminate special cases. Scan the target for:
    • Boolean flag arguments or module-level toggles that gate behavior.
    • Hardcoded branch paths that duplicate a general case.
    • Numeric or string domain constants used as inline guards. For each found artifact, either refactor the boolean branch into a data-driven lookup, merge the special case into the general path, or convert the magic constant into a named constant with a documented invariant. Done when: no boolean flags, hardcoded duplicate branches, or inline magic constants remain.
  5. Re-validate. Run checks by compiling the target in its language-native build and running the existing test suite scoped to the target. If the project has no compile step, run the test suite alone. If any check fails, halt with INVARIANT-FAIL: <identifier> listing the specific failure. Record the complete set of removed special-case artifacts as the resolution log. Done when: all invariant checks pass and the resolution log is complete.

Read the full file on GitHub · 46 lines

Files

What ships with it

1 file 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. 4d ago Changed · -7 tokens per session 8d880dd6a961
  2. 6d ago First seen · 46 lines · 54 tokens per session scan A 2dccba997500

Subscribe to this mod's changes

universal-invariant-baseline is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 837 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 2026-09-04.

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