Borrowing it
Nothing to install: this file belongs to Alexander-M-Dickerson/ai-asset-pricing. 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/Alexander-M-Dickerson/ai-asset-pricing/main/AGENTS.mdgit clone --depth 1 https://github.com/Alexander-M-Dickerson/ai-asset-pricingWrote 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/alexander-m-dickerson/ai-asset-pricing/agents-md)<a href="https://agentmods.dev/instructions/alexander-m-dickerson/ai-asset-pricing/agents-md"><img src="https://agentmods.dev/badge/instructions/alexander-m-dickerson/ai-asset-pricing/agents-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/alexander-m-dickerson/ai-asset-pricing/agents-md"><img src="https://agentmods.dev/badge/instructions/alexander-m-dickerson/ai-asset-pricing/agents-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 | $0.01512 | $0.01512 |
| Opus 5 | $0.00756 | $0.00756 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
ai-asset-pricing AGENTS.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 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Empirical Finance Agent Guide
This repository is designed to work well with Codex, Claude Code, and Gemini CLI.
For Codex, this file is the primary routing layer. For Claude, the .claude/
surface remains active, but the shared source of truth for repo-wide behavior
should live in docs/ai/. Gemini CLI uses GEMINI.md which imports this file.
Core Contract
- Read
docs/ai/core.mdbefore making cross-cutting repo decisions. - When machine-specific paths or tools matter, use the canonical local state reported by
tools/bootstrap.py audit. - Treat canonical local state as external to the repo by default.
- Treat repo-root
LOCAL_ENV.md/CLAUDE.local.mdas optional compatibility shims, not the source of truth. - Treat
.claude/settings.local.jsonas ignored maintainer-local Claude state; never commit it. - Never commit
LOCAL_ENV.md,CLAUDE.local.md, or.claude/settings.local.json. - Run
tools/release_preflight.py --strictbefore a shared release. - Strict preflight auto-cleans repo temp artifacts when possible and tolerates gitignored repo-root local artifacts such as
.venv/,venv/,.claude/settings.local.json,.tmp-pytest-current/,.tmp-uv-cache/, and.Rhistory;LOCAL_ENV.mdandCLAUDE.local.mdstill block a release-ready tree. - Gemini CLI uses
GEMINI.mdwhich imports this file. SeeGEMINI.mdfor Gemini-specific notes.
Task Routing
- Setup, onboarding, tool paths, or first-run issues:
- Read
docs/ai/onboarding.md - Prefer
tools/onboard.ps1ortools/onboard.shfor true cold-start onboarding - Use
tools/onboard_driver.pyafter Python exists - Use
tools/bootstrap.py audit - Execute the required commands from the audit report's
bootstrap_plan - Use
tools/bootstrap.py apply - Treat
tools/bootstrap.py repair --write-canonical-stateas a direct-terminal fallback, not the primary Codex path - Treat
tools/onboard_probe.pyas the shared probe implementation, not the user-facing entry point - Ask once whether the user has WRDS and wants it configured now; WRDS is optional and onboarding can still succeed without it
- Use repo-root compatibility shims only if they were explicitly generated for a private single-user working copy
- Read
- WRDS, data extraction, or query pipelines:
- Read
docs/ai/wrds.md - CRSP v2 is the default for all new work — see
docs/ai/wrds.md"CRSP Version Policy" - Then read the relevant
.claude/agents/*.mdfile for deep domain detail
- Read
- PyBondLab package work:
- Read
docs/ai/pybondlab.md - Then read
packages/PyBondLab/AGENTS.md
- Read
- Research ideation, brainstorming, or developing new paper ideas:
- Read
.claude/skills/idea/SKILL.md - The skill creates lightweight
projects/{mnemonic}_idea/workspaces withmusings.md(adversarial dialogue log),literature.md(verified references), andresearch_plan.md(evolvable paper skeleton) - Conventions for
*_idea/folders are in.claude/rules/idea-workspace.md - When an idea graduates to a full project, use
docs/ai/onboarding.mdpatterns to create theprojects/{mnemonic}/scaffold via/new-project - The
research_plan.mdoutput is designed to feed into.claude/skills/build-context/SKILL.mdand.claude/skills/write-section/SKILL.mddownstream
- Read
- Writing, LaTeX, referee responses, or decks:
- Read
docs/ai/writing.md - For new papers, start from
boilerplate/template_main.texandboilerplate/template_references.bib - Use
.claude/skills/setup-paper/SKILL.mdto scaffold a project'slatex/folder from that boilerplate - For paper-aware editing or audits, check
guidance/paper-context.mdin the active project if it exists, or generate it via.claude/skills/build-context/SKILL.md - Auditing workflows live in
.claude/skills/audit-section/SKILL.md,.claude/skills/full-paper-audit/SKILL.md,.claude/skills/check-consistency/SKILL.md,.claude/skills/audit-captions/SKILL.md,.claude/skills/audit-math/SKILL.md, and.claude/skills/outline/SKILL.md - Writing rules include
.claude/rules/academic-writing.md,.claude/rules/latex-conventions.md,.claude/rules/latex-citations.md,.claude/rules/banned-words.md,.claude/rules/grammar-punctuation.md, and.claude/rules/referee-reply.md - Then read the relevant
.claude/skills/*.mdfile for the concrete workflow
- Read
- Figures, charts, plotting, Word proof packs, or visual validation:
- Read
docs/ai/figures.md - Use
fintools.figuresbefore writing custom plotting code - Use
style="fins"for the house publication style andstyle="ft"for FT-style output - Use
tools/figure_examples.py --style ft --docx --output results/figuresor--style finsto recreate validation galleries - Keep
.claude/skills/publication-figures/legacy helper assets available for explicitly requested standalone helper workflows - Keep generated PNG/PDF/DOCX/caption outputs under ignored
results/figures/paths
- Read
- Context maintenance:
- Run
tools/context_drift.pyto detect stale documentation - Use
/sync-context(Claude Code) to review and apply targeted doc updates
- Run
- Editing
.claude/files:- Keep
docs/ai/authoritative for shared rules - Do not duplicate repo-wide guidance if a shared doc already covers it
- Keep
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 · 78 lines · 1,512 tokens per session scan A 66d93a7d02ca
ai-asset-pricing AGENTS.md is an instructions file published in the GitHub repository Alexander-M-Dickerson/ai-asset-pricing (59 stars, last pushed 4mo ago), licensed MIT. It adds 1,512 tokens to every session, about $0.0076 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).