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/tax-planning-memo)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/tax-planning-memo"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/tax-planning-memo/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/tax-planning-memo"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/tax-planning-memo.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 | $0.00019 | $0.00885 |
| Opus 5 | $0.00010 | $0.00443 |
| Sonnet 5 | $0.00004 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
tax-planning-memo 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 13d 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 tax-planning memo — a short, organized set of planning ideas for a client, framed as opportunities to evaluate rather than promises. Tax law changes every year and depends on the client's facts, so the memo's job is to surface ideas and flag what to verify, never to harden into unverified specifics.
What to ask for (only if the user hasn't provided it)
Ask conversationally for whatever's missing:
- Client name and entity type (individual, sole prop, S-Corp, partnership, C-Corp)
- Tax year the memo covers
- Planning horizon (year-end, quarterly, multi-year)
- Their situation this year (income up/down, big events — sold a business, bought equipment, new child, retirement contributions, RSUs vesting)
- Planning ideas the accountant wants covered (retirement contributions, entity considerations, timing of income/expenses, estimated payments, charitable strategy, depreciation)
- Any figures the accountant wants used (income, projected liability, contribution room)
- Deadlines the accountant wants referenced
Output
A clear, organized memo:
- Situation — 2–3 sentences summarizing where the client stands, using only figures the accountant provided
- Planning ideas — each idea gets a short heading, a plain-language explanation of the opportunity, and what it depends on. Frame as "worth evaluating," "likely beneficial if…," never "you will save $X."
- Action items — concrete next steps, with any deadlines the accountant supplied (or
[verify current due date for tax year / return type / jurisdiction]) - What to confirm — the facts or figures the accountant needs to nail down before acting
Before you send — current-law check
After the memo — separated by a horizontal rule — append a compact checklist. Include only what applies:
- ✓ Facts and figures as provided — one line confirming every number and provision traces to what the accountant gave you (nothing invented).
- Verify-placeholders to resolve — list any
[verify tax-year figure],[verify citation], or[verify current due date …]you left in. - Verify before sending — eligibility/thresholds framed as "likely / verify" rather than definitive; no guaranteed savings; state/local and entity-type variations flagged where relevant.
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.
- 13d ago First seen · 55 lines · 19 tokens per session scan A d761e94fa789
tax-planning-memo is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 885 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
ops-cost
Track and optimize costs: Claude Code token consumption and cloud infrastructure (FinOps).
legal-payment
Payment integration and subscription management.
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.