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 fixed-view-visual-benchmarkgit 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/fixed-view-visual-benchmark)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/fixed-view-visual-benchmark"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/fixed-view-visual-benchmark.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00823 |
| Opus 5 | $0.00016 | $0.00411 |
| Sonnet 5 | $0.00006 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
fixed-view-visual-benchmark 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 yesterday.
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.
Fixed-view visual benchmark
Contract
| Field | Bound contract |
|---|---|
| Trigger | A visual needs repeatable fixed-view rendering and independent rubric scoring. |
| Authority | Human-gated: asks for capture consent before rendering; otherwise reversible local: writes only named local artifacts; rollback is undo. No remote mutation. |
| Side effect | Fixed-view visual benchmark: renders and scores the fixed view against the frozen rubric. |
| Done | The saved render clears the frozen rubric threshold. |
| Stop | Stalled; render blocked; budget exhausted. Bound: fixed view rig, rubric threshold, render budget. |
Inputs
- Fixed view rig (required): camera position and orientation, scene definition, render settings (resolution, samples, lighting, post-processing). All parameters that affect the rendered output must be named and frozen.
- Frozen rubric threshold (required): the minimum aggregate score that defines a passing render, plus the rubric dimensions and their weights.
- Render budget (required): the maximum render attempts or time allowed, declared before work begins.
Procedure
- Bind the fixed view rig, rubric threshold, and render budget. Freeze all three before any mutation. Done when: the rig, threshold, and budget are named and frozen.
- Capture consent. Ask for and record explicit human consent before rendering. Done when: consent is recorded.
- Render the fixed view through a specified rendering interface with reproducibility controls. The interface must accept the frozen rig parameters and produce a deterministic output: same camera, same scene, same settings, same result. Record the interface name, version, and the exact parameter set used. If the interface is non-deterministic (stochastic sampling, temporal effects), declare the seed or averaging strategy that makes repeated renders comparable. Done when: a render is produced from the frozen rig with the interface and parameters recorded.
- Score the render against the frozen rubric independently. The rubric defines scoring dimensions (for example: composition, lighting accuracy, material fidelity, geometric correctness), each with a weight summing to 1.0 and a 0–10 scale per dimension. The aggregate score is the weighted sum. Score each dimension against the rubric criteria, not against the previous render. Record per-dimension scores, the aggregate, and the threshold. Done when: the rubric score is recorded with per-dimension breakdown.
- Stop at success (aggregate score clears the threshold), any non-success terminal, or the bound. Done when: a terminal class is reached and named.
- Persist the run record to
.outline/loops/fixed-view-visual-benchmark/<run_id>/when durable. Emitreceipt.jsonbefore return. Done when: the receipt is written with the saved render path, per-dimension scores, aggregate, threshold, and terminal class.
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.
- yesterday First seen · 44 lines · 32 tokens per session scan A 3a33ccfa49d7
fixed-view-visual-benchmark is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 823 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 2026-09-06.
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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…