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 run-smoke-testsgit 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/run-smoke-tests)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/run-smoke-tests"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/run-smoke-tests/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/run-smoke-tests"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/run-smoke-tests.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 | $0.00043 | $0.00817 |
| Opus 5.5 | $0.00017 | $0.00327 |
| Sonnet 5.5 | $0.00009 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
run-smoke-tests 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run smoke tests
Contract
| Field | Bound contract |
|---|---|
| Trigger | Explicit human request to run end-to-end smoke verification |
| Authority | Reversible local changes only: write only named local artifacts; state the rollback path before mutating |
| Side effect | Builds, runs tests, and may apply minimal fixes to local files only |
| Done | Check set passes: stable smoke result with honest flake risk classification |
Inputs
- Required: working directory containing a runnable build and test suite.
- Optional: named smoke-test command or target (defaults to the project's conventional smoke target).
- Required: network access if the build or tests retrieve remote artifacts.
Procedure
- Audit scope. Record the current VCS state (branch, HEAD commit) as the rollback anchor. If the workspace is dirty, stop and report the dirty state before proceeding.
- Identify smoke target. Locate the project's conventional smoke-test target in the build manifest (Makefile, package.json scripts, Cargo.toml, pyproject.toml, or equivalent). Use the user-supplied target name if one was given.
- Validate target existence. Verify the target exists and is executable before running it. If absent, stop with
target-missing. - Run smoke. Execute the smoke target. Capture stdout, stderr, and the exit code.
- Classify result. Known flaky candidates are tests or targets listed in the project's flake manifest, quarantine list, skip file, or user-supplied input. If none are declared, classify non-zero exits as
failand mark flake-suspect unknown.- Exit 0 with no stderr:
pass. - Exit 0 with stderr warnings:
pass-with-warnings. - Non-zero exit with a known flaky candidate:
flake-suspect. - Non-zero exit with no known flaky candidate:
fail.
- Exit 0 with no stderr:
- Minimal fix attempt (authority-gated). If the result is
failorflake-suspectand the failure has one recognizable cause (missing import, typo, broken symlink, incorrect env-var), apply the minimal correction directly. Do not refactor, add features, or widen scope. Re-run the smoke target once after the fix. - Rollback rule. If the second run still fails, revert all changes made in step 6 before reporting.
- Report. Emit the final classification, run count, any diffs applied and reverted, and the rollback anchor.
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.
- 1mo ago First seen · 51 lines · 43 tokens per session scan A 2c2cbc3a7600
run-smoke-tests is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 26d ago), licensed Apache-2.0. It adds 43 tokens to every session and 817 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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.