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.
npx skills add OutlineDriven/odin-claude-plugin --skill lighter-checksgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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.
[](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/lighter-checks)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/lighter-checks"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/lighter-checks/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.
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/lighter-checks"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/lighter-checks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.00828 |
| Opus 5 | $0.00024 | $0.00414 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
lighter-checks 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lighter checks
Contract
| Field | Bound contract |
|---|---|
| Trigger | Checking has started to loop, a check would re-run against untouched code, a second tool would prove what the first proved, or the user asks to stop over-checking and ship. |
| Authority | Read commands and emit a delivery decision only; do not mutate files, version control, credentials, paid services, publications, deployments, or remote state. |
| Side effect | Run scoped typecheck, lint, and test verification once per touched language, trim redundant verification, and report whether delivery may proceed. |
| Done | One proving action has run per claim, no action was repeated for reassurance, each touched language's complete project gate ran once, and the result is delivered on the first green gate. |
Inputs
Required inputs are the claims to prove, the changed files or explicitly bounded changed surface, the languages touched, and the project's typecheck, lint, and test commands for those languages. Supplied results must include their command, scope, and outcome. Never assume an optional input establishes evidence.
Procedure
-
Bound verification to the supplied changed surface and touched languages. If either is unknown, stop rather than inspect or verify unrelated scope. Done when: the changed surface and touched languages are bounded, or the skill stops for unknown scope.
-
Map each claim to the narrowest action that directly proves it. Reuse a supplied result only when its command and scope cover that claim and the relevant code has not changed since it ran. Done when: every claim is mapped to one narrowest proving action or a reused result that covers it.
-
Remove any proposed re-run against unchanged code and any second tool that covers the same failure class as an accepted result. Keep a second action only if it proves a distinct claim or failure class. Done when: no redundant re-runs or duplicate-class tools remain in the plan.
-
Run the project's complete typecheck, lint, and test gate once for every touched language. Use the narrowest project-supported scope that still covers the changed surface; use a repository-wide command only when no narrower command covers it. Done when: one complete gate has run per touched language.
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.
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.
- 6d ago First seen · 44 lines · 48 tokens per session scan A 4544f3b7a088
lighter-checks is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 828 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…