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 panaversity/ca-cpa-practice-agents --skill audit-methodologygit clone --depth 1 https://github.com/panaversity/ca-cpa-practice-agentsWrote 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/panaversity/ca-cpa-practice-agents/audit-methodology)<a href="https://agentmods.dev/skills/panaversity/ca-cpa-practice-agents/audit-methodology"><img src="https://agentmods.dev/badge/skills/panaversity/ca-cpa-practice-agents/audit-methodology/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/panaversity/ca-cpa-practice-agents/audit-methodology"><img src="https://agentmods.dev/badge/skills/panaversity/ca-cpa-practice-agents/audit-methodology.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 | $0.00030 | $0.01617 |
| Opus 5 | $0.00015 | $0.00809 |
| Sonnet 5 | $0.00006 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
audit-methodology 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Methodology Extension
Purpose
This extension encodes a firm's audit methodology standards as standing instructions for the assurance agent. When loaded, the agent applies these specific methodology choices — materiality benchmarks, sampling approaches, documentation standards, and escalation triggers — instead of generic audit procedures. Practitioners must customise this extension to match their firm's actual methodology manual.
Instructions
Materiality Calculation Methodology
When calculating materiality for an audit engagement, apply the following framework:
Step 1 — Select the benchmark:
- For-profit entities: Pre-tax profit from continuing operations (primary benchmark).
- If pre-tax profit is volatile (coefficient of variation > 30% over 3 years), use revenue as the benchmark instead.
- Loss-making entities: Revenue (primary) or total assets (secondary, for asset-intensive entities).
- Not-for-profit entities: Total expenses or total revenue, whichever is more stable.
- Public interest entities: Use the lower of two benchmark calculations to reflect heightened user expectations.
Step 2 — Apply the percentage:
- Pre-tax profit benchmark: 5% (standard), 3-4% (public interest entities or higher-risk engagements).
- Revenue benchmark: 0.5% to 1% (use the lower end for entities with tight margins).
- Total assets benchmark: 1% to 2%.
- Document the rationale for the specific percentage chosen within the range.
Step 3 — Calculate performance materiality:
- 65% of overall materiality (standard engagements).
- 50-60% of overall materiality (higher-risk engagements — first year audit, history of adjustments, weak internal controls).
- Document the risk factors that determined the percentage.
Step 4 — Set the trivial threshold (Clearly Trivial):
- 5% of overall materiality.
- Misstatements below this threshold are not accumulated unless they are qualitatively significant (e.g., related party, management remuneration, fraud).
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 · 134 lines · 30 tokens per session scan A 25f0a83f5419
audit-methodology is a skill published in the GitHub repository panaversity/ca-cpa-practice-agents (5 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,617 once invoked, about $0.0002 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.