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 agentmods add skills/alebgl77/claude-inc/audit-supportnpx skills add alebgl77/claude-inc --skill audit-supportgit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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/alebgl77/claude-inc/audit-support)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/audit-support"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/audit-support.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.01119 |
| Opus 5 | $0.00051 | $0.00560 |
| Sonnet 5 | $0.00020 | $0.00224 |
| Haiku 4.5 | $0.00010 | $0.00112 |
Grade A, and why
audit-support 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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Support — Auditor
"Prep for audit."
When to use
- An audit is scheduled — "fieldwork starts August 3, get us ready".
- The request list landed — "here's the auditor's PBC, organize and track it".
- Samples arrived — "they picked 25 invoices, do we have support for each?".
- Findings need answers — "draft management responses to these three findings".
- Balances must be provable — "build tie-outs for cash, AR, and fixed assets".
Workflow
- Scope the audit. Period, framework, first-year vs recurring, and the areas that matter — load the TB or statements with code and rank areas by balance and activity, never by guesswork.
- Build the PBC list by area (cash, AR/revenue, inventory, fixed assets, AP/accruals, debt, equity, payroll, tax): each item gets description, owner, expected format, due date, status. Merge with the auditor's own list when one exists — their naming wins.
- Draft walkthrough narratives for revenue, purchases, and payroll: trigger event → documents created → systems touched → approvals → how it hits the GL, with control points tagged inline (e.g., [C1: 2-way match]). One page per cycle, specific to this company — no boilerplate.
- Match samples to support. For each sampled item, list required documents (invoice, PO/contract, delivery or acceptance evidence, payment proof), check what exists, and mark complete / partial (naming the gap) / absent. Find the gaps before the auditor does.
- Build tie-out schedules per tested area: GL balance → subledger or supporting schedule → financial statement line, computed in code, with differences explained or proven zero.
- Run the open-items tracker: item, area, requested by, owner, due date, status, blocker — sorted by due date, overdue flagged.
- Draft finding responses: restate the finding neutrally, give root cause, management response, and remediation with a named owner and target date. Factual and specific — no defensiveness, no over-promising.
- Package. Write
PBC-<period>.md(or .xlsx), the walkthroughs, tie-outs, and tracker; refresh the tracker as items close.
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.
- 5d ago First seen · 74 lines · 101 tokens per session scan A b2562109f798
audit-support is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 1,119 once invoked, about $0.0005 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 skills, from other repositories
company-cfo
Monthly CFO workflow for a company or agency — pull raw data from bank + payment processor + payroll + expense management, categorize and reconcile, compute end-of-month cash via transaction-sum method, update a scenario projector for forward forecasting, write the monthly snapshot report, surface decisions to…
personal-cfo
When you want to model personal financial scenarios — house purchase + rental income (ADU, bedroom rentals, house-hacking), renovation budgets, monthly cash flow forecasts, big-purchase decisions, savings/investment what-ifs. For personal life: a household (you + partner), household budgets, real-estate decisions.…
mcp-lark
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
crypto-report
Get cryptocurrency market data. Get Binance AI analysis report. Get blockchain news updates.
black-swan
Activate when: user says 'this can't happen,' 'never happened in N years,' 'our models say it's near-zero'; user is stress-testing a strategy or portfolio against extreme scenarios; someone mentions fat tails, Taleb, narrative fallacy, or turkey problem; a past catastrophic event is being analyzed and it 'seemed…
expected-value-and-kelly
Activate when: user asks 'how much should I bet/invest on this?', 'what's the expected value here?', 'Kelly criterion', 'optimal bet size', 'fractional Kelly', 'how big a position should I take?', or is allocating capital across repeated decisions (ad spend by segment, VC portfolio construction, position sizing, A/B…