Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/workspace-deep-auditWrote 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/workspace-deep-audit)<a href="https://agentmods.dev/skills/mishahanin/heading-os/workspace-deep-audit"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/workspace-deep-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/workspace-deep-audit"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/workspace-deep-audit.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 | $0.00198 | $0.03990 |
| Opus 5 | $0.00099 | $0.01995 |
| Sonnet 5 | $0.00040 | $0.00798 |
| Haiku 4.5 | $0.00020 | $0.00399 |
Grade A, and why
workspace-deep-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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Deep Audit
CEO-only manual gate. Produces the v1/v2-equivalent comprehensive workspace audit on demand — same 8-section format, same level of detail, same evidence-backed claim discipline. Never auto-triggers. This is the skill the CEO invokes when a major milestone, strategic decision, or demonstrable artifact requires a full re-audit of the entire ecosystem.
This skill is read-only against the workspace. It produces output files in outputs/operations/workspace/ and logs to threads/business/ but never modifies any workspace infrastructure (rules, skills, scripts, configs, datastore). Fix-application belongs to /scrutinize, not here.
When to Use
- Major workspace milestone (post-sprint, post-rollout, end of quarter, before strategic decision)
- Producing a demonstrable artifact of work done (board presentation, partner pitch, internal review)
- Detecting drift over time (run quarterly + use
--vs=<prev_audit>to surface deltas) - Categorical positioning question (where does the workspace stand vs the public landscape)
When NOT to Use
- Single-skill review →
/evaluate - Specific fix scrutiny →
/scrutinize - Quick operational health check →
/state-check - Morning operational brief →
/dashboard - End-of-week CEO review →
/weekly-review
Arguments
| Arg | Default | Purpose |
|---|---|---|
--mode=full |
full | 8-section deep audit (45-90 min run, 5,000-8,000 words) |
--mode=quick |
— | 6-section audit, skips competitive + best-practices analysis (~20 min, 2,500 words) |
--mode=focus |
— | requires --focus={subsystem}; produces single-subsystem deep dive |
--focus={subsystem} |
— | skills / rules / deps / security / architecture / observability |
--vs=<path> |
— | Delta mode — compare current state against the previous audit at <path>; output explicit before/after tables |
Example invocations:
/workspace-deep-audit— full audit (default)/workspace-deep-audit --mode=quick— fast 6-section pass/workspace-deep-audit --vs=outputs/operations/workspace/2026-05-14_audit_workspace-deep-overview.md— delta vs v1/workspace-deep-audit --mode=focus --focus=security— security-only deep dive
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 · 289 lines · 198 tokens per session scan A dd7d3103a6ef
workspace-deep-audit is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 198 tokens to every session and 3,990 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
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-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-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-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.