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 canopusgit 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/canopus)<a href="https://agentmods.dev/skills/mishahanin/heading-os/canopus"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/canopus/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/canopus"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/canopus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 249 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00111 | $0.03682 |
| Opus 5 | $0.00056 | $0.01841 |
| Sonnet 5 | $0.00022 | $0.00736 |
| Haiku 4.5 | $0.00011 | $0.00368 |
Grade A, and why
canopus 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 9d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canopus
The standard for building anything non-trivial here. Seven steps, two of them the operator's own. Every mechanical part is built out of git, GitHub and pytest rather than re-implemented in Python. One shell command defeated 93 percent of the retired version's hand-built prevention surface.
The one thing this exists to prevent: a contract too weak to decide anything, passing as one that decided. Across all 62 prior records a contract was never once weakened after the fact, and was born too weak thirty times. The green to distrust is the one no wrong implementation was ever made to fail.
Bare /canopus — the seven steps
Nothing is run. Show the agenda below and name the step the work in hand is at. Read that position from the conversation, never from the disk. Only steps 4 and 7 leave a trace in this repository, so a position read off it is a guess dressed as a measurement.
The seven steps
The agenda has exactly one definition, scripts/utils/canopus_steps.py. This
file may summarise it and may never renumber it.
1. Define the Value
2. superpowers:brainstorming -> scope document
3. superpowers:writing-plans -> plan
4. /scrutinize the plan, apply every finding -> the operator's commit
5. superpowers:subagent-driven-development -> implementation
6. /scrutinize --relentless, apply every finding
7. Production
Steps 4 and 7 are the operator's. The seven steps fall into four acts:
- Act 1, steps 1 to 4. Nothing is built yet.
- Act 2, step 5. The implementer is not the planner.
- Act 3, step 6. Green is not the same as right.
- Act 4, step 7. The undo is named before anyone needs it.
Step 3 — what makes a plan worth committing
Four properties, and a plan missing any of them buys nothing at step 4. The
authoring detail behind properties 1 and 4 is references/planning-gate.md. It
carries the five contract-writing rules, each earned by a measured failure, and
how to read probe's table. Read it before writing a contract.
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.
- 9d ago First seen · 293 lines · 111 tokens per session scan A 24357685a500
canopus is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 111 tokens to every session and 3,682 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.