Borrowing it
Nothing to install: this file belongs to azazhang/finance-literature-review-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/azazhang/finance-literature-review-skill/main/GEMINI.mdgit clone --depth 1 https://github.com/azazhang/finance-literature-review-skillWrote 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/instructions/azazhang/finance-literature-review-skill/gemini-md)<a href="https://agentmods.dev/instructions/azazhang/finance-literature-review-skill/gemini-md"><img src="https://agentmods.dev/badge/instructions/azazhang/finance-literature-review-skill/gemini-md/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/instructions/azazhang/finance-literature-review-skill/gemini-md"><img src="https://agentmods.dev/badge/instructions/azazhang/finance-literature-review-skill/gemini-md.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 | $0.00871 | $0.00871 |
| Opus 5.5 | $0.00348 | $0.00348 |
| Sonnet 5.5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
finance-literature-review-skill GEMINI.md 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 26d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finance Literature Review Context
When a task involves finance, macro-finance, banking, accounting, corporate finance, asset pricing, disclosure, governance, or adjacent economics literature, use a finance-first review workflow.
Dynamic Search & Venue Order
- Core Top Finance Journals: Journal of Finance, Journal of Financial Economics, Review of Financial Studies.
- Subfield Leading Finance: JFQA, Review of Finance, Management Science (finance), RCFS, RAPS, JMCB, JCF, JBF.
- Adjacent Top Economics Journals: AER, QJE, JPE, Econometrica, ReStud if the mechanism, macro transmission, or identification overlaps.
- Top Accounting Journals: The Accounting Review, Journal of Accounting Research, Journal of Accounting and Economics, Review of Accounting Studies, CAR when overlapping disclosure, earnings, auditing, governance, or information environment.
- Dynamic Working Paper Integration:
- Never automatically rank working papers at the bottom.
- Tier 1 Working Papers: NBER Working Papers (
CF,AP,ME,PE), CEPR Discussion Papers, Central Bank series (Federal Reserve Board FEDS, NY Fed, BIS, ECB, SEC DERA), active Revise & Resubmit (R&R) at Top 3/Top 5, and premier conference papers (AFA, WFA, EFA, NBER Summer Institute). - Frontier vs. Mature Topics: On frontier/emergent topics (e.g., GenAI in finance, private debt, 2023 bank runs), Tier 1 working papers sit co-equal with top journal publications. On mature topics, published articles provide the bedrock.
- Systematic Working Paper Discovery: SSRN FEN eJournals, NBER programs, CEPR, annual conference programs (AFA, WFA, EFA, NBER SI), RePEc/IDEAS NEP reports, and finance JEL codes (
G1,G2,G3,M4,E4/E5).
Hard Rules & Abstract Quarantine
- Zero Citation Invention: Never invent citations, authors, publication years, or venue tiers.
- Abstract Quarantine: Never infer identification strategies, fixed effects, clustering, or economic magnitudes from an abstract alone. If only the abstract is accessible, tag
[Abstract-Only Provisional], preface statements with "Author claims in abstract (unverified): ...", and mark design fields unverified. Abstract-only papers cannot establish definitive ownership or declare research gaps settled. - 3-Anchor Introduction Protocol: Retrieve the Introduction (Paras 3–11) and baseline table notes to verify: (1) Setting & specific exogenous shock, (2) Quantitative magnitude, (3) Self-stated contribution relative to benchmark papers.
- Intellectual Lineage: Distinguish Theoretical Originator $\rightarrow$ Empirical Landmark $\rightarrow$ Causal ID Benchmark $\rightarrow$ Boundary Reassessment.
- Track Granular Empirical Attributes: Record research question, primary dataset/infrastructure (Compustat, CRSP, Dealscan, Call Reports, HMDA, TRACE), sample period and filters, unit of observation, specific exogenous shock / source of variation, fixed effects structure, standard error clustering, main result, mechanism, and boundary conditions (what the paper leaves open).
- Synthesize by Mechanism & Design: Prefer synthesis by economic transmission channel and causal design over paper-by-paper chronological summaries.
- Transparent Evidence Limits: If the evidence base is thin, preprint-heavy, or only abstracts are available, say so directly.
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.
- 26d ago Changed · +7 lines · +645 tokens per session a21b10ed8f49
- 1mo ago First seen · 28 lines · 226 tokens per session scan A 1ad1c22be4f5
finance-literature-review-skill GEMINI.md is an instructions file published in the GitHub repository azazhang/finance-literature-review-skill (1 stars, last pushed 27d ago), licensed MIT. It adds 871 tokens to every session, about $0.0035 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.