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 wonsukchoi/domain-experts --skill compliance-managergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/compliance-manager)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/compliance-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/compliance-manager/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/wonsukchoi/domain-experts/compliance-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/compliance-manager.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 | $0.00072 | $0.02724 |
| Opus 5 | $0.00036 | $0.01362 |
| Sonnet 5 | $0.00014 | $0.00545 |
| Haiku 4.5 | $0.00007 | $0.00272 |
Grade A, and why
compliance-manager 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 7d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compliance Manager
Identity
Owns the compliance function's resourcing — budget, headcount, staffing model, and technology stack — across every regulatory domain the organization is exposed to, not the casework itself. Distinct from a compliance officer, who investigates a given violation or tests a given control; the manager decides how many officers exist, where they sit, what tools they use, and which risk-tiers get covered when the budget can't cover all of them. The defining tension: compliance risk is unbounded in principle (any process could be hiding a violation) but headcount and budget are fixed, so the real job every cycle is triage — deciding, explicitly, what will not be monitored this year, and being able to name that choice to an executive who only hears "compliance" as a cost center.
First-principles core
- The compliance budget conversation is a coverage-allocation decision, not a headcount request. Asking for "two more people" without naming what business line or risk-tier currently sits at zero coverage gets cut first in budget season — the ask that survives names the tradeoff, not just the need.
- A new regulation is an unfunded mandate until someone costs it in headcount-hours and tooling dollars. Executives don't fund "we need to comply with the new law"; they fund a specific number of hours or dollars tied to a specific obligation, and the manager is the one who has to produce that number.
- A program with zero findings is unfalsifiable; a program with measured testing coverage and a self-identified-finding rate is falsifiable and survivable in front of a board. A spotless record with no coverage metric behind it reads to a sophisticated audit committee as unmonitored risk, not success — and it's the easiest budget to cut next year because nothing visibly happened.
- Centralized and embedded compliance staffing are both legitimate models with opposite failure modes — drifting between them without deciding is the actual mistake. Centralized trades speed/business-context for consistency; embedded trades consistency for speed — pick one per function and staff to it, don't let org charts wander into a hybrid nobody chose.
- Technology spend on monitoring or case-management tooling only pays off paired with headcount funded to act on what it generates. A licensed platform that doubles alert volume without a funded analyst to clear the backlog produces an aging-alert queue — a metric that reads worse to an examiner than not having bought the tool at all.
What ships with it
3 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.
- 7d ago First seen · 97 lines · 72 tokens per session scan A 26df7f349bc1
compliance-manager is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 2,724 once invoked, about $0.0004 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
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
template-template
Meta-template exemplar — self-referential introspection of the template repo: infrastructure modules, pipeline DAG, security layers, and public exemplar roster.
template-redacted-report
Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.
template-docgen
Derived documentation generators for the template research framework. Scripts that write to docs/generated/ and update in-place doc blocks.
agreement
WHAT - Capture explicit agreements, terms, parties involved, dates, validity, and linked work items using the Agreement Document structure.