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 humansense2systemgit 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/humansense2system)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/humansense2system"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/humansense2system/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/humansense2system"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/humansense2system.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 | $0.00074 | $0.00939 |
| Opus 5.5 | $0.00030 | $0.00376 |
| Sonnet 5.5 | $0.00015 | $0.00188 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
humansense2system 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humansense → system
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to compile taste and "this feels wrong" into tokens, rules, forbidden combinations, and examples |
| Authority | reversible-local: write only the named local artifact; state the rollback path |
| Side effect | One structured rule/pattern document written to the project shared docs or agent-rule folder |
| Done | At least one classified entry exists across any section (Forbidden, Tokens, Examples, or Rules) and the user has validated the artifact |
Inputs
Must be supplied:
- Target artifact path — a file under the project shared docs or an agent-rule folder that stores the human's agent-facing patterns
Optional:
- Existing patterns — any prior rule/pattern document at the same path; the procedure merges into it
Procedure
-
Elicit raw taste signals. Ask the user for concrete cases where the outcome felt wrong, off, or missing, rather than abstract preferences. Record each as a named signal with the observable behavior, not the inferred cause. Stop when the user says they have listed what they can.
-
Classify each signal. For every named signal, ask the user to place it into one bucket:
- FORBIDDEN: must never happen
- TOKEN: a named flag or category the agent can recognize and route on
- EXAMPLE: a concrete input-output pair that defines what is acceptable
- RULE: a conditional statement (if-then) that captures the boundary
If the user cannot classify a signal, discard it rather than guess.
-
Write the artifact. If the target file does not yet exist, create it with the full template, including the top-level
# Agent Taste Guide — [project name]heading:# Agent Taste Guide — [project name] ## Forbidden - [ONE LINE: observable behavior that must never occur] ## Tokens - `[token-name]`: description of what the agent should recognize and route on ## Examples ### Correct - [concrete input → concrete acceptable output] ### Incorrect - [concrete input → concrete wrong output] ## Rules - [if condition, then behavior]
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 · 75 lines · 74 tokens per session scan A 9b70627480d3
humansense2system is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 27d ago), licensed Apache-2.0. It adds 74 tokens to every session and 939 once invoked, about $0.0003 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…
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…
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…