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 Agentic-Assets/corbis-literature-starter-kit --skill finance-idea-screeninggit clone --depth 1 https://github.com/Agentic-Assets/corbis-literature-starter-kitWrote 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/agentic-assets/corbis-literature-starter-kit/finance-idea-screening)<a href="https://agentmods.dev/skills/agentic-assets/corbis-literature-starter-kit/finance-idea-screening"><img src="https://agentmods.dev/badge/skills/agentic-assets/corbis-literature-starter-kit/finance-idea-screening/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/agentic-assets/corbis-literature-starter-kit/finance-idea-screening"><img src="https://agentmods.dev/badge/skills/agentic-assets/corbis-literature-starter-kit/finance-idea-screening.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 | $0.00040 | $0.03206 |
| Opus 5 | $0.00020 | $0.01603 |
| Sonnet 5 | $0.00008 | $0.00641 |
| Haiku 4.5 | $0.00004 | $0.00321 |
Grade A, and why
finance-idea-screening 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 12d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finance Idea Screening
Turn rough topics into credible paper ideas or kill weak ideas early.
Stage 0: Desk-editor screen
Before running the full literature search and scoring workflow, answer four questions in 1-2 sentences each:
- Prior-changing: What broad finance prior would change if this paper is right?
- Zero-result value: Why would the paper still matter if the main estimate is zero or the sign flips?
- Question over method: Is the question more important than the shock, instrument, or dataset?
- Desk read: Could this clear a top generalist journal's desk read today?
If two or more answers are weak, return Revise or Kill before investing in the full search chain.
Framing rule: If the one-sentence summary starts with "Using a novel dataset..." or "Exploiting a policy shock...", force a rewrite until it starts with the finance question. The question must come first; the data or design is the tool, not the contribution.
What counts as a strong idea
A strong idea scores well on six dimensions:
- Sharp question — Can you state the research question in one sentence without hedging? Is there a clear dependent variable and a testable prediction?
- First-order importance — Would the answer change priors in a broad finance literature or on a materially important market, policy, or contracting problem? Would a generalist finance editor care even if the estimated effect is zero?
- Verified contribution — Relative to the 3-5 closest papers, is the novelty real and nontrivial? Novelty must be in mechanism, question, identification, measurement, or implication, not just in setting, time period, or data access. "X but in country Y" or "X but with newer data" is not a contribution unless the setting variation generates a genuinely different economic prediction.
- Economic mechanism — Is there a friction, incentive, or equilibrium force that generates a testable prediction? Can you name the channel and distinguish it from obvious alternatives?
- Convincing theory-to-evidence bridge — Is there a persuasive inferential bridge from idea to evidence? This can be a quasi-experiment, field experiment, theory model, structural estimation, validated measurement exercise, sufficient-statistic approach, or out-of-sample asset-pricing test. Judge whether the bridge matches the question, not whether it looks like a standard causal design.
- Data, measurement, and replication feasibility — Three sub-checks:
- Access: Can the data realistically be obtained in time?
- Construct validity: Does the empirical measure actually map to the mechanism? Would a skeptic accept it as a reasonable proxy?
- Replication feasibility: Could the core result be documented and replicated under current top-journal data and code sharing policies?
What ships with it
1 file 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.
- 12d ago First seen · 215 lines · 40 tokens per session scan A 79443f035baf
finance-idea-screening is a skill published in the GitHub repository Agentic-Assets/corbis-literature-starter-kit (11 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 3,206 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 2026-08-30.
Other skills, from other repositories
fin-viz-launch
A tool for turning research data and a written description into academic charts. It can choose a suitable chart type, create plotting code with matplotlib or seaborn, and save the result as a high-resolution PDF, SVG, or PNG.
finance
Runtime subject skill payload for finance subject activation.
review-response
Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.
chief-financial-officer
Owns the financial position: planning, budgeting, forecasting, unit economics, cash, and the numbers the business is run and reported on. Use this to build or challenge a budget, model a decision's financial consequence, assess unit economics or runway, evaluate an investment or spend request, set financial controls…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
payroll-operations
Runs the pay cycle so it is right, on time, and provable — the calendar and cutoffs, what feeds pay from the HRIS and time systems, gross-to-net and the deductions in it, multi-jurisdiction registration and tax filing, off-cycle payments and corrections, and the reconciliation to the general ledger. Use this to design…