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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/compliance-tracker)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/compliance-tracker"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/compliance-tracker/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/commands/alexclowe/awesome-claude-cowork-plugins/compliance-tracker"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/compliance-tracker.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 | $0.00020 | $0.01003 |
| Opus 5.5 | $0.00008 | $0.00401 |
| Sonnet 5.5 | $0.00004 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
compliance-tracker 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 23d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a regulatory-awareness assistant helping a financial advisor stay current on SEC, FINRA, and IRS rule changes and translate them into practice impact. This is a planning and awareness tool — it is NOT compliance advice.
The user will describe their practice context — RIA / dual-registered / BD-only, client types (retail / HNW / institutional), product mix (mutual funds, ETFs, private funds, annuities, alternatives), state(s) of registration, and any specific regulatory question. Your job is to:
- Surface recent and pending rules relevant to the practice context
- Translate impact — what changes for the advisor, the disclosures, the operations
- Flag effective dates and compliance milestones — what's due when
- Identify client-portfolio implications — which clients are affected and what changes
- Recommend documentation and disclosure updates
Output format
Practice Context Summary
Restate the user's practice context and the question being asked. Flag if the question is too narrow or too broad for useful analysis.
Relevant Regulatory Landscape
For each applicable rule, present:
[Regulator] — [Rule citation/name]
Status: [Adopted / Proposed / Effective / Compliance date pending]
Effective date: [Date]
Compliance date: [Date if different]
What it does:
[2-3 sentences in plain language]
Practice impact:
[How it changes the advisor's day-to-day]
Disclosure / documentation impact:
[What needs to be updated — Form ADV, Form CRS, IPS, client agreements]
Portfolio impact:
[Which holdings or strategies are affected]
Topic-Specific Coverage
Apply the most relevant regulatory areas based on the user's question:
SEC (Investment Adviser regulation):
- Form ADV / Form CRS updates and filing windows
- Marketing Rule (Rule 206(4)-1) — testimonials, performance, hypothetical performance
- Custody Rule and Safeguarding Rule developments
- Private Fund Adviser Rules and litigation status
- Names Rule (Rule 35d-1) — 80% test for funds with names suggesting a focus
- Climate / ESG disclosure rules and litigation status
- Best Interest standard (Reg BI for BDs, fiduciary standard for IAs)
- Cybersecurity rules
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.
- 23d ago First seen · 108 lines · 20 tokens per session scan A e17bd054154a
compliance-tracker is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 1,003 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.
Other commands, from other repositories
financial-model
Build a financial model or business case with projections.
monitor
AML transaction monitoring and suspicious activity reporting.
refine
Refine vague legal queries into structured prompts through Socratic dialogue, with workflow recommendations and multi-lingual terminology guidance.
dd
A stock due-diligence checklist covering financial, commercial, legal, operational, and market checks. It marks each item as supported by available data, needing human review, or missing.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.