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 strict-validation-setupgit 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/strict-validation-setup)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/strict-validation-setup"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/strict-validation-setup/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/strict-validation-setup"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/strict-validation-setup.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 | $0.00061 | $0.02401 |
| Opus 5.5 | $0.00024 | $0.00960 |
| Sonnet 5.5 | $0.00012 | $0.00480 |
| Haiku 4.5 | $0.00006 | $0.00240 |
Grade A, and why
strict-validation-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strict validation setup
Contract
| Field | Bound contract |
|---|---|
| Trigger | User invokes a strict-mode validation or verifiable-goals loop setup. |
| Authority | Reversible local write: idempotent tooling-config merge, per-task GOALS.md scaffold, and failing-test authoring; no remote, credential, or deployed mutation. |
| Side effect | Merges strict-mode tooling configs idempotently, ensures AGENTS.md points to per-task GOALS.md, scaffolds .agent-tasks/<id>/GOALS.md, and writes failing tests; one-shot bootstrap. |
| Done | Strict configs are merged idempotently and per-task GOALS.md plus failing tests are in place, with task goals kept out of AGENTS.md. |
Inputs
- User goal (required): enough observable behavior to derive at least one pass/fail success criterion. If not observable, stop before writing and ask for the missing outcome.
- Task ID (optional): must match
^[a-z0-9][a-z0-9-]{0,63}$. If absent, usetask-followed by the first 12 lowercase hexadecimal characters of SHA-256 over the exact UTF-8 user-goal text. - Overwrite authorization (optional): permits replacement of a named conflicting non-strict config value. It does not permit replacing unrelated configuration or whole files.
- Project root (required): contains exactly one supported primary ecosystem: TypeScript, Python, Rust, Go, or OCaml. A TypeScript project may also contain
package.json; that pair is one ecosystem.
This skill reads or creates AGENTS.md only to ensure one stable pointer: Per-task goals live in .agent-tasks/<task-id>/GOALS.md. It never writes task-specific criteria there and never reads or edits CLAUDE.md.
Refusal
no-supported-manifest: name the supported manifests; write nothing.multiple-ecosystems: name all detected primary manifests; require one explicit project scope; write nothing.unsupported-ecosystem: name the detected ecosystem and stop without a false reference claim. C++, Java, Kotlin, Spring Boot, Nest-specific, and React-specific setup are unsupported.config-conflict: name the path, key, current value, and required value; require explicit overwrite authorization for that key.config-shape-unsupported: name the manifest/config shape that cannot be merged without a partial or destructive rewrite; write nothing.goal-not-observable: ask for the missing observable outcome before writing.test-framework-missing: name the supported frameworks for the ecosystem; do not add dependencies or generic tests.task-test-location-unsupported: explain why the existing runner cannot execute.agent-tasks/<id>/tests; write nothing rather than claiming failing tests are in place.agents-task-content: name the task-specific AGENTS.md lines; write nothing until the user chooses how to separate them.task-path-conflict: name each existing unrelated or conflicting task file; overwrite nothing.write-failed: restore every prior target byte-for-byte and remove only newly created files.verification-mismatch: restore the complete write set; report expected and actual path/key or criterion.
What ships with it
7 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.
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.
- 1mo ago First seen · 84 lines · 61 tokens per session scan A b0cd46323f03
strict-validation-setup is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,401 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…