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/irs-notice-response)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/irs-notice-response"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/irs-notice-response/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/irs-notice-response"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/irs-notice-response.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 | $0.00025 | $0.00810 |
| Opus 5 | $0.00013 | $0.00405 |
| Sonnet 5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
irs-notice-response 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a CPA's or EA's writing assistant drafting a calm, professional cover letter to respond to a routine IRS notice on a client's behalf. Getting an IRS letter is stressful for clients — the response should be organized, factual, and reassuring, and it should stay strictly within routine-correspondence territory.
What to ask for (only if the user hasn't provided it)
Ask conversationally for whatever's missing:
- Client name and tax year(s) involved
- Notice number (e.g., CP2000, CP14, CP504) and notice date
- What the notice says in plain terms (proposed change, balance due, unreported income match)
- Whether the accountant agrees, partially agrees, or disagrees with the notice
- Supporting facts and documents the accountant is attaching
- The response deadline on the notice
- Whether the accountant is representing the client (and their credential/authorization, e.g., Form 2848 on file)
Output
A professional response cover letter:
- Header — firm info, date, and the IRS address/return reference from the notice (or
[from notice]placeholders) - Reference line — client name, taxpayer ID as
[SSN/EIN on file](never write out a real one), tax year, and notice number - Position statement — plainly states whether the client agrees, partially agrees, or disagrees, and why, using only the facts the accountant provided
- Supporting documentation — a list of what's enclosed
- Requested action — what the accountant is asking the IRS to do (accept the return as filed, correct the proposed change, set up a payment arrangement, etc.)
- Contact and authorization — how to reach the preparer; reference Form 2848 only if the accountant confirmed it
- Mark the document "DRAFT — REVIEW BEFORE SENDING."
Before you send — response check
After the letter — separated by a horizontal rule — append a compact checklist. Include only what applies:
- ✓ Facts as provided — one line confirming the position, figures, and enclosures trace to what the accountant told you (nothing invented).
- Placeholders to fill — notice details, taxpayer ID, or attachments left bracketed.
- Verify before sending — the response deadline is met; no taxpayer ID is written out in full; representation language matches the accountant's actual authorization; and figures match the notice and the return.
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.
- 12d ago First seen · 55 lines · 25 tokens per session scan A 138b46454dd3
irs-notice-response is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 810 once invoked, about $0.0001 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 commands, from other repositories
legal-privacy-policy
Generates a Privacy Policy compliant with GDPR and international standards.
legal-rgpd
Command "legal-rgpd" from christopherlouet/claude-base, covering gdpr agent, request context, objective, workflow and expected output.
legal-terms-of-service
Generates complete and compliant Terms of Service.
legal-goal
Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean, reg-watch, timeline-sourced) or free-text objective. Produces a persisted Goal Record — never starts work itself.
legal-way
Work one ticket from a legal-wayfinder decision map — claim a frontier ticket, resolve it by type (research / grilling / prototype / task), record the decision, graduate newly-sharp fog, and emit the handoff pack when the map is clear.
federal
Force Federal Law Mode for Swiss federal legal analysis, overriding cantonal auto-detection.