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 setup-bennygit 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/setup-benny)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/setup-benny"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/setup-benny.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00073 | $0.00824 |
| Opus 5 | $0.00036 | $0.00412 |
| Sonnet 5 | $0.00015 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
setup-benny 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 3d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install automation pack
Contract
| Field | Bound contract |
|---|---|
| Trigger | User needs to install a third-party automation pack or template repository safely and deterministically |
| Authority | Reversible local write (hash-guarded rollback). Explicit human invocation starts the install; preview every target and consequence before writing |
| Side effect | Fetches the source archive to a scratch location, verifies all files against expected hashes, applies placeholder transformations, and atomically moves files to the target directory |
| Done | The pack is installed in the target directory and passes safety checks |
Inputs
- Source archive URL (required): the URL to fetch the pack or template repository from.
- Target directory (required): the local path where the pack will be installed.
- Expected file manifest with hashes (required): a mapping of file paths to expected SHA-256 hashes, used to verify every extracted file.
- Required file transformations (required): placeholder replacements keyed by strict unique anchors, applied to specified files after extraction.
Procedure
- Fetch the source archive to a scratch location. Download the archive from the source URL to a temporary directory. Done when: the archive is downloaded and extracted to the scratch location.
- Verify all extracted files against the expected manifest and blob IDs. For every file in the extracted tree, compute its SHA-256 hash and compare against the expected manifest. Fail with hash mismatch if any file's hash does not match. Done when: every extracted file's hash matches the expected manifest.
- Apply required transformations using strict unique anchors. For each transformation: locate the unique anchor string in the target file, replace it with the specified value, and confirm the anchor was found exactly once. Fail if an anchor is not found or appears more than once. Done when: all transformations are applied and every anchor was found exactly once.
- Check the target directory for conflicts. If the target directory exists and contains files, compare each existing file's hash against the managed-state manifest from a prior install. Block if existing files differ from managed state, indicating manual modifications. Done when: the target directory is confirmed empty or matches prior managed state.
- Atomically move files to the target and save the applied manifest for rollback. Move all files from the scratch location to the target directory in one operation. Write the applied manifest (file paths, post-transformation hashes, and the original source URL) to a managed-state file beside the target for rollback on future runs. Done when: all files are moved to the target and the applied manifest is saved.
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.
- 3d ago First seen · 43 lines · 73 tokens per session scan A ae1907336be0
setup-benny is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 824 once invoked, about $0.0004 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…
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…