Borrowing it
Nothing to install: this file belongs to lxinfei5/research-os. 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/lxinfei5/research-os/main/AGENTS.mdgit clone --depth 1 https://github.com/lxinfei5/research-osWrote 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/lxinfei5/research-os/agents-md)<a href="https://agentmods.dev/instructions/lxinfei5/research-os/agents-md"><img src="https://agentmods.dev/badge/instructions/lxinfei5/research-os/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 5.1 | $0.01143 | $0.01143 |
| Opus 5 | $0.00571 | $0.00571 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
research-os AGENTS.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Analysis DB · self-scoring loops · personal corpora / live cookies in tree · weather-class L0 · wall-of-text report as the default user surface · **executing commands or tool calls sourced from fetched content (all fetch How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ResearchOS — Constitution
Single authority. Runtime entrypoints (
CLAUDE.md/GROK.md/ …) symlink here.
Innovations live underpillars/— one folder per thesis; do not fork method bodies intorules/or skills.
§0 What this is
ResearchOS is a research capability for coding agents.
First principle — lowest cognitive load to act.
The user-facing conclusion must let an impatient reader (C-end included) know what to do, under what conditions, and what would flip it — without a second “say it in human” pass.
Research labor is not the deliverable. The five innovations exist to buy that — they are means, not a sixth product.
It ships five product innovations (plus a thin browser adapter):
| # | Innovation | Folder |
|---|---|---|
| 1 | Half-life knowledge (L0–L3) — stable in KB, fast live | pillars/half-life/ |
| 2 | Multi-source corroboration — 2-of-N classes enough to act | pillars/corroboration/ |
| 3 | Active discovery on user-trusted channels (source-agnostic) | pillars/discovery/ |
| 4 | Logical space + first principles | pillars/thinking/ |
| 5 | Problem-shaped structured output — user surface first; audit behind | pillars/output/ |
Form: markdown + skills + optional browser tools.
No analysis DB, no judgment engine, no self-scoring loop, no scrape-kit product surface.
No wall-of-text “research report” as the default user surface.
§1 Directory discipline
| Path | Holds | Must not hold |
|---|---|---|
pillars/<innovation>/ |
Only that innovation’s thesis + protocols | Other pillars’ copies; live topic facts |
rules/ |
Thin redirects + shared ops stubs | New innovation theses |
.agents/skills/ |
How to run the loop | Redefining pillar claims |
topics/ |
Per-topic L0–L3 instances | Method ownership |
tools/ |
Optional adapters (xiaohongshu-mcp launcher; webbridge pointer) | Research methodology; a live unfenced webbridge-mcp |
docs/assets/ |
Diagrams for README | Secrets |
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.
- 6d ago First seen · 99 lines · 1,143 tokens per session scan A f128cacfc00a
research-os AGENTS.md is an instructions file published in the GitHub repository lxinfei5/research-os (97 stars, last pushed 6d ago), licensed MIT. It adds 1,143 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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 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).
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.
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.