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 Qiushen-first/cn-investment-banking-skills --skill cn-ib-diligence-workpapergit clone --depth 1 https://github.com/Qiushen-first/cn-investment-banking-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/qiushen-first/cn-investment-banking-skills/cn-ib-diligence-workpaper)<a href="https://agentmods.dev/skills/qiushen-first/cn-investment-banking-skills/cn-ib-diligence-workpaper"><img src="https://agentmods.dev/badge/skills/qiushen-first/cn-investment-banking-skills/cn-ib-diligence-workpaper/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/qiushen-first/cn-investment-banking-skills/cn-ib-diligence-workpaper"><img src="https://agentmods.dev/badge/skills/qiushen-first/cn-investment-banking-skills/cn-ib-diligence-workpaper.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 | $0.00131 | $0.01149 |
| Opus 5.5 | $0.00052 | $0.00460 |
| Sonnet 5.5 | $0.00026 | $0.00230 |
| Haiku 4.5 | $0.00013 | $0.00115 |
Grade A, and why
cn-ib-diligence-workpaper 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 2mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CN IB Diligence Workpaper
Turn unstructured evidence into a reproducible workpaper that links objective, population, procedure, evidence, exception, conclusion, reviewer, and closure.
Principles
- Start from the diligence objective, not from the available files.
- Preserve population, period, entity, sample method, and evidence provenance.
- Separate factual evidence, management explanation, analyst calculation, and professional conclusion.
- Never infer
no exceptionfrom missing evidence. - Record contradictory evidence rather than selecting the more convenient source.
- Do not claim sponsor, legal, or accounting sign-off. Route judgment to the responsible professional.
- Apply confidentiality and personal-data minimization. Never place live bank-account or identity data in public examples.
Workflow
1. Define the workpaper objective
State:
- assertion or risk addressed;
- entity and period;
- population and completeness source;
- materiality or review threshold;
- planned procedure;
- expected evidence;
- responsible preparer and reviewer.
Read references/workstreams.md for common workstreams. Tailor the objective to the transaction instead of copying a generic checklist.
2. Build the population
Before selecting samples or summarizing findings:
- identify the source system or source schedule;
- record extraction date and preparer;
- reconcile population totals to an independent record where possible;
- preserve excluded records and exclusion rationale;
- mark incomplete populations as a scope limitation.
Do not treat a management-prepared list as complete without a completeness procedure.
3. Select and document procedures
Possible procedures include:
- inspection;
- recalculation;
- external confirmation;
- interview;
- database or public-record search;
- source-to-ledger tracing;
- ledger-to-source vouching;
- cross-document comparison;
- analytical review;
- full-population rule scan;
- risk-based or statistical sampling.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 149 lines · 131 tokens per session scan A 349c26350a91
cn-ib-diligence-workpaper is a skill published in the GitHub repository Qiushen-first/cn-investment-banking-skills (101 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 131 tokens to every session and 1,149 once invoked, about $0.0005 per session on Opus 5.5. 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.
cn-ib-diligence-workpaper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cn-ib-diligence-workpaperQiushen-first/cn-investment-banking-skills | Skill | 101 | 2mo ago | Apache-2.0 | A | 131 | Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 14 | Claude Code, Codex |
| comps-analysisNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 13 | Claude Code, Codex |
| tear-sheetanthropics/financial-services | Skill | 41k | 9d ago | Apache-2.0 | A | 143 | Claude Code |
| lbo-modelanthropics/financial-services | Skill | 41k | 9d ago | Apache-2.0 | A | 57 | Claude Code |
| pitch-deckanthropics/financial-services | Skill | 41k | 9d ago | Apache-2.0 | A | 73 | Claude Code |
| ppt-template-creatoranthropics/financial-services | Skill | 41k | 9d ago | Apache-2.0 | A | 51 | Claude Code |