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-doc-chasegit 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-doc-chase)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/cpa-doc-chase"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/cpa-doc-chase/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-doc-chase"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/cpa-doc-chase.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 | $0.00121 | $0.02380 |
| Opus 5 | $0.00060 | $0.01190 |
| Sonnet 5 | $0.00024 | $0.00476 |
| Haiku 4.5 | $0.00012 | $0.00238 |
Grade A, and why
cpa-doc-chase 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 10d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPA — Client Document Chase
Not legal or tax advice. Verify required documentation against your engagement letter, firm standards, and current IRS/state guidance. No penalty rates, retention periods, extension effects or plan-funding deadlines appear here — all of them expire. Route every such question to current authority rather than supplying a remembered figure, including inside a message drafted for a client. The practitioner who signs owns the file.
Activate when: an engagement cannot progress without client materials; a client has gone silent; you are drafting a document request or a follow-up; a deadline is approaching and the chase has not converged; you are handing an engagement to a colleague and need the blocking state written down. Do NOT activate when: the materials are complete; the question is how to treat an item you already have.
Why this skill
Engagements rarely stall on technical difficulty. They stall on paperwork that never arrives, and then on follow-up that is polite, unstructured, and ignored.
The specific failure: a flat alphabetical list of twenty missing items produces either paralysis or delivery of the five easiest. Neither unblocks you. The fix is to sort by what an item blocks, not by what it is, and to escalate on a fixed clock rather than on how the preparer feels that week.
Process
1. Frame the engagement. Engagement type and year · entity types and jurisdictions · prior-year working papers available · hard deadline and whether extension exists · who actually holds the documents (often a bookkeeper or spouse, not the signer) · preferred channel and past response pattern · fee status. Mark anything unknown as UNKNOWN — an unknown here is itself a finding.
Gate: no prior-year file and no engagement letter → you are scoping, not chasing. Scope first.
2. Mine the prior year. Walk last year's return or working papers line by line: what document supported this, and do I have it yet? This finds what a generic checklist never will — the K-1 from a partnership the client forgot they hold, the state they moved out of mid-year.
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.
- 10d ago First seen · 129 lines · 121 tokens per session scan A 281119ab2a79
cpa-doc-chase is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 121 tokens to every session and 2,380 once invoked, about $0.0006 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
invoice-chase
Runs collections on late invoices: builds an aging ladder (current/30/60/90+), assigns each invoice a rung on an escalation sequence with ready-to-send emails — friendly nudge, firm reminder with late-fee mention, final notice — plus a phone script, tone rules that preserve the relationship, a chase log, and…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…
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…
tax-prep
Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar template, a clean handoff pack for the…
audit-support
Gets the books audit-ready: builds the PBC (prepared-by-client) list by area, drafts walkthrough narratives for key cycles (revenue, purchases, payroll), matches auditor samples to support, prepares tie-out schedules, tracks open items with owners and due dates, and drafts responses to findings. Use when the user says…
financial-statements
Builds a full statement set — P&L, balance sheet, and indirect cash flow — from a trial balance or transaction export, mapping accounts to a standard chart and proving every tie-out in code. Use when the user says 'build a P&L from this trial balance', 'turn this export into financials', 'I need a balance sheet for…