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 deciqAI/knowledge-skills --skill cpa-form-findergit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote 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/deciqai/knowledge-skills/cpa-form-finder)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/cpa-form-finder"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/cpa-form-finder/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/deciqai/knowledge-skills/cpa-form-finder"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/cpa-form-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00163 | $0.02814 |
| Opus 5 | $0.00081 | $0.01407 |
| Sonnet 5 | $0.00033 | $0.00563 |
| Haiku 4.5 | $0.00016 | $0.00281 |
Grade A, and why
cpa-form-finder 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 11d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPA — Form Finder
Not legal or tax advice. This maps situations to form families only. No thresholds, limits, rates, phase-outs, eligibility tests or dates appear here — all of them expire. Verify against current IRS instructions for the applicable year and the relevant state authority.
Activate when: scoping, quoting, or building a document request; a client describes something you want to place quickly; checking that a prepared return has the schedules its facts imply. Do NOT activate when: the question is a number, a limit, or a deadline; the return is already prepared and the question is whether it is right — that is [cpa-return-review].
Why this skill
A client says "I sold some crypto, my wife started consulting, and we have a rental in another state." In that sentence are six forms, two states, and three questions you need answered before you can quote the job.
The output of this skill is always two lists — forms likely in scope, and what you still have to determine. The second is the more useful one. A form list without its open questions reads as a conclusion, and it is not one.
Process
1. Decompose. Clients describe their year as a story; forms attach to events. For each element capture: what happened or what status holds · type (income / deduction / credit / information reporting / election / status) · which taxpayer or entity · timing, including whether it spans years · jurisdiction.
Gate: ask about location for every element, separately. The most common scoping error is a missed jurisdiction, not a missed form — a rental elsewhere, months of remote work, a mid-year move, an owner living in a different state from the entity. Each can add a filing nobody priced.
2. Map to form families.
Form 1040 and schedules — Schedule 1 (additional income and adjustments) · Schedule 2 (additional taxes) · Schedule 3 (additional credits) · Schedule A (itemized) · Schedule B (interest and dividends) · Schedule C (sole proprietorship) · Schedule D with Form 8949 (capital asset sales, including digital assets) · Schedule E (rental, royalty, pass-through) · Schedule F (farming) · Schedule H (household employees) · Schedule SE (self-employment) · Schedule 8812 (qualifying children and other dependents).
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.
- 11d ago First seen · 154 lines · 163 tokens per session scan A f5932518b503
cpa-form-finder is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 163 tokens to every session and 2,814 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
legal-risk-assessment
Severity-by-likelihood legal risk register for a situation or deal — enumerates concrete risks, scores each one impact 1-5 × likelihood 1-5, renders a heat-map table, attaches mitigations to every risk at or above threshold, defines escalation criteria for immediate human counsel, and sets monitoring triggers. Use…
review-contract
Clause-by-clause contract review — inventories key clauses (term, termination, liability cap, indemnity, IP, payment, confidentiality, governing law, auto-renewal), flags deviations from market-standard positions with RED/YELLOW/GREEN severity and verbatim quotes, drafts redline language, and sets negotiation…
signature-request
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
klauselinhalt-und-verbote-pruefen
Prüft eine AGB-Klausel anhand von Kontrollfähigkeit, gesetzlichen Klauselverboten und Interessenabwägung. Für B2C und B2B; liefert ein Klauselvotum mit Leitbild, Gegenposition und konkreter Rechtsfolge.