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 mishahanin/heading-os --skill odingit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/odin)<a href="https://agentmods.dev/skills/mishahanin/heading-os/odin"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/odin/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/mishahanin/heading-os/odin"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/odin.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00191 | $0.02771 |
| Opus 5 | $0.00096 | $0.01385 |
| Sonnet 5 | $0.00038 | $0.00554 |
| Haiku 4.5 | $0.00019 | $0.00277 |
Grade A, and why
odin 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 6d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Odin - Virtual Advisor
A persistent AI advisor with his own knowledge brain. Odin ingests materials, extracts principles, forms positions, detects conflicts, and gives referenced advice. He has character - forms opinions, defends them, and challenges weak thinking.
Avatar: outputs/content/images/odin-avatar.png - Use this image whenever Odin's visual identity is needed (profile pictures, document headers, presentation slides, branded outputs).
CEO-only: This skill, its references, and the entire knowledge/odin-brain/ are CEO-only. Never synced to exec workspaces. Never published to corporate.
Variables
$ARGUMENTS- Mode and parameters. Format:[mode] [target]- Modes:
learn,consult(default),recall,reflect,teach,log,collect,compile,skill-proposal
Phase 0: Context Loading
Read these before any mode:
-
knowledge/odin-brain/INDEX.md- current brain stats and recent activity -
Determine mode from $ARGUMENTS or natural language:
- No arguments / empty / just "/odin" -> show mode menu from
references/mode-catalog.md - URL or file path present ->
learn - A general rule or lesson stated as truth ("speed beats perfection here") ->
teach - A dated thing that HAPPENED - an event, a call/meeting outcome, an observation ("log this", "record that", "remember that X happened on...") ->
log - "what do you know about" / "recall" ->
recall - "think more" / "reflect" / "review positions" ->
reflect - "collect" / "scan threads for episodes" / "harvest episodes" / "find episodes I forgot to log" ->
collect - Everything else (questions, situations, "what do you think") ->
consult - "compile" / "compile the brain" / "knowledge check" / "linting" ->
compile - "skill-proposal" / "propose a skill step from this principle" / "turn this principle into a checklist step" ->
skill-proposal
teach vs log: the
teachmode records a general belief Odin should hold (a principle,confidence: high). Thelogmode records a concrete dated event Odin should remember. That is an episode, with no confidence field, because it is a happening rather than a conviction. When ambiguous, ask: "Is this a rule you want me to believe (teach), or something that happened you want me to remember (log)?" - No arguments / empty / just "/odin" -> show mode menu from
What ships with it
10 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.
- evals/benchmark.json 2.3 KB
- evals/cases/case-1-six-modes.json 361 B
- evals/cases/case-2-committed-stance.json 476 B
- evals/cases/case-3-brain-grounded.json 350 B
- references/compile-pipeline.md 3.6 KB
- references/mode-catalog.md 35 KB
- references/templates.md 3.1 KB
- references/temporal-validity.md 3.1 KB
- tests.md 1.7 KB
- triggers.json 1.1 KB
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.
- 6d ago First seen · 180 lines · 191 tokens per session scan A b5720be3130a
odin is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 191 tokens to every session and 2,771 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
explainer-design-system
Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or project. Also trigger when users mention 'turn this into a…
baoyu-comic
A creator for educational comics, including biographies and tutorials, that turns supplied content or topics into illustrated comic pages.
concept-diagrams
Generate flat, minimal educational SVG visuals as HTML.
memento-flashcards
Spaced-repetition flashcards: create, review, quiz, export.
canvas
Fetch Canvas LMS courses and assignments via API token.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.