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 instructions/lambenthan/empiricalwiki/agents-mdgit clone --depth 1 https://github.com/Lambenthan/empiricalwikiWrote 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/lambenthan/empiricalwiki/agents-md)<a href="https://agentmods.dev/instructions/lambenthan/empiricalwiki/agents-md"><img src="https://agentmods.dev/badge/instructions/lambenthan/empiricalwiki/agents-md.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 | $0.00523 | $0.00523 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
empiricalwiki 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 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.
What it actually says
EmpiricalWiki — Agent Entry Point
This file exists so that any coding agent (Codex, Cursor, Claude Code, ...) can operate this repo. The authoritative runtime schema lives in
CLAUDE.md— read it first and follow it exactly. Everything below is a minimal orientation, not a replacement.
What this repo is
A Karpathy-style LLM wiki specialized for empirical research in accounting, finance, management, and economics. Three layers:
raw/— user-owned sources (PDF/tex). Read-only for agents, with two exceptions: external fetches go toraw/discovered/, generated sidecars go toraw/tmp/(append-only).wiki/— the LLM-maintained, compounding artifact. Typed markdown pages with strict frontmatter and bidirectional[[wikilinks]].- Schema —
CLAUDE.md+.claude/skills/*/SKILL.mddefine how to read, write, and link.
Hard constraints (full list in CLAUDE.md)
raw/papers/,raw/notes/,raw/web/are user-owned: never modify or overwrite.wiki/graph/is derived state: never hand-edit; maintain it only throughtools/research_wiki.py(add-edge,add-citation,rebuild-context-brief,rebuild-open-questions).- Every forward link requires its backward link (cross-reference table in CLAUDE.md).
wiki/index.mdis updated on every ingest;wiki/log.mdis append-only.- Page templates:
docs/runtime-page-templates.zh.md. Theory-paper skeleton:docs/runtime-theory-skeleton.zh.md.
Operations
- Skills (slash commands) live in
.claude/skills/<name>/SKILL.md. Agents without a skill runner can open the SKILL.md and follow it as a procedure. Core loop: ingest (/empirical-ingest,/theory-ingest,/ingest) → query (/ask) → lint (/check). - Setup:
./setup.sh --lang zh(Windows:setup.ps1 -Lang zh). - Python: prefer
.venv/bin/python; tools auto-load~/.envand project.envviatools/_env.py. - Local website view of the wiki:
tools/view.sh(Quartz, read-only).
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 · 29 lines · 523 tokens per session scan A ee64e78b9552
empiricalwiki AGENTS.md is an instructions file published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 523 tokens to every session, about $0.0026 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
example-project AGENTS.md
AGENTS.md instructions for eweisbrod/example-project, covering agents.md - ai assistant context for example-project, repo role, repo structure, when working in this repo and common pitfalls.
example-project CLAUDE.md
Claude Code instructions for eweisbrod/example-project, a project described as: Template for an Accounting or Finance Research Project.
superpowers-zh CLAUDE.md
Claude Code instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
spec-kit-zh AGENTS.md
AGENTS.md instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
openaccountants CLAUDE.md
Claude Code instructions for openaccountants/openaccountants, covering openaccountants — agent instructions, for ai agents landing here, repository overview, skill file conventions and audit flash point convention.
pm-copilot AGENTS.md
AGENTS.md instructions for Leo-maomao/pm-copilot, covering pm copilot repository guidance, runtime loading, boundaries and verification.