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 brain-auditgit 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/brain-audit)<a href="https://agentmods.dev/skills/mishahanin/heading-os/brain-audit"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/brain-audit/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/brain-audit"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/brain-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 12 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00090 | $0.02440 |
| Opus 5 | $0.00045 | $0.01220 |
| Sonnet 5 | $0.00018 | $0.00488 |
| Haiku 4.5 | $0.00009 | $0.00244 |
Grade A, and why
brain-audit 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brain-audit - post-synthesis audit primitive
A small composable skill. Takes a list of source file paths and an optional entity name. Runs three checks against the sources. Returns a stable markdown footer that the composing skill pastes beneath its synthesis.
The skill does not synthesize, does not query a workspace-wide index, does not write state. It reads the files passed in and scans canonical workspace locations for the named entity. It then runs one LLM call to detect source disagreements, and emits a three-section footer.
CEO may also invoke directly for ad-hoc audits.
Phase 1: Argument parsing and sanity checks
1.1 Parse arguments
Read $ARGUMENTS:
--sources <paths>(required): comma-separated. Each path is workspace-relative (paths starting with/,c:\, or containing..traversal are rejected as invalid sources in Phase 1.2). Workspace paths in this repo do not contain commas; if a future path does, the composer must quote it. If--sourcesis absent or empty, return the no-sources footer (Phase 3.5) and exit.--entity <name>(optional): scopes the modality scan. If absent, modality check is skipped and the footer notes "no entity specified."--modalities <list>(optional): comma-separated subset of the canonical list. Default is "all fromreferences/modalities.md."
1.2 Validate source paths
For each path:
- File exists -> keep in source set.
- File missing -> drop from source set, list under "sources not found" in the footer.
- Path outside workspace root -> drop, list under "invalid sources" in the footer.
1.3 Degenerate cases
- Zero valid sources -> return no-sources footer (Phase 3.5), exit.
- Single valid source -> run Phase 2.1 (dates) and Phase 2.2 (modality), skip Phase 2.3 (contradictions). Footer notes "single source, no comparison."
- More than 20 sources -> cap at 20 for the contradiction check (LLM context budget), keep all sources for the date check. Footer notes the cap.
Phase 1 produces no user-visible output on success. All edge cases produce a valid (degraded) footer rather than an error. The composing skill must never see a stack trace.
What ships with it
5 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.
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 · 246 lines · 90 tokens per session scan A 862a327fc762
brain-audit is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 90 tokens to every session and 2,440 once invoked, about $0.0005 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.