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/adimango/ai-adoption-playbooknpx agentmods add skills/adimango/ai-adoption-playbook/ai-exposure-registerWrote 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/adimango/ai-adoption-playbook/ai-exposure-register)<a href="https://agentmods.dev/skills/adimango/ai-adoption-playbook/ai-exposure-register"><img src="https://agentmods.dev/badge/skills/adimango/ai-adoption-playbook/ai-exposure-register/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/adimango/ai-adoption-playbook/ai-exposure-register"><img src="https://agentmods.dev/badge/skills/adimango/ai-adoption-playbook/ai-exposure-register.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 | $0.00055 | $0.05899 |
| Opus 5 | $0.00028 | $0.02950 |
| Sonnet 5 | $0.00011 | $0.01180 |
| Haiku 4.5 | $0.00006 | $0.00590 |
Grade A, and why
ai-exposure-register 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 3d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Exposure Register
Purpose
Collects one record per AI use case actually running in the company — what it does, who owns it, what data it reads, and whether it can act on its own. Produces the exposure section of the board report: four counts, a per-function rollup, and an exceptions list with named owners and due dates.
This is the missing input to a question the framework already asks. reporting-readiness-assessment Risk Posture Q4 asks how AI use cases are classified by risk tier, and Q5 asks about EU AI Act readiness. Neither can be answered honestly without a list of use cases, and no other skill produces one. Without this register, Risk Posture is an opinion about a register that does not exist.
Core principle: Ask about behaviour, not capability. A leader cannot reliably answer "can it write to your CRM?" They can answer "when it finishes, does something appear in HubSpot on its own, or do you click something first?" Capability questions get guesses. Behavioural questions get facts.
Four columns, a minute per entry. The register is four things: what it is, who owns it, whether it can act without a person, and what data it touches. That is the whole first pass, and it is a complete deliverable — not a draft. Six more fields exist, but they are only collected for the handful of records that earn them.
This staging is the design, not a shortcut. People abandon inventories halfway. A four-column register covering the whole company beats a ten-field one that stopped at Engineering, and the second is what you get if you ask everything about everything.
This register observes. It does not restrict. The speed advantage smaller companies have comes from people being able to wire up what they need without raising a ticket. Permissions and monitoring exist on most of these platforms, but they are hard to run well, and tightening them is the fastest way to remove what made the company quick. The register's job is to make the exposure visible and give the sharp cases a name and a date — not to become a gate. Read the output as a short, targeted exception list, never as an argument for locking the platform down.
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.
- 3d ago First seen · 340 lines · 55 tokens per session scan A 76c3131808e5
ai-exposure-register is a skill published in the GitHub repository adimango/ai-adoption-playbook (23 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 5,899 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
vendor-review
Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.
entity-compliance
Entity compliance tracker — initialize, report upcoming deadlines, update status, run health audit, export to CSV. Maintains a compliance-tracker.yaml built from the entity table, calculates filing deadlines by entity and jurisdiction, and surfaces what's due in the next 30/60/90 days. Use when user says "entity…
integration-management
Post-closing M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initializes from whatever deal artifacts are available (purchase agreement, deal summary, closing checklist) and connects to deal-context.md and closing-checklist.yaml from the M&A cold-start.…
matter-workspace
Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when…
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
performance-management
Runs performance systems that change behavior — expectations, feedback, review cycles, calibration, and handling underperformance. Use this to design or fix a review process, run calibration, write or coach on feedback, address sustained underperformance, or work out why reviews consume weeks and change nothing.