Home / pengqianhan / ai-human-research-os · GitHub

AGENTS.mdA

AGENTS.md from pengqianhan/ai-human-research-os is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned

mdr add pengqianhan/ai-human-research-os/AGENTS.md@git:20260930.4bad615

Pins git:20260930.4bad615 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 14 of 14 checks passed
Kind: AGENTS.md file
Repository: pengqianhan/ai-human-research-os
Path: AGENTS.md
Versions recorded: 5
Latest version: git:20260930.4bad615, committed Sep 30, 2026
First version recorded: Sep 23, 2026
Size: 6,988 bytes
Repository stars: 3
License: MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# AI-Human Research OS Instructions

A file-system-native environment serving the human's long-horizon research.
Organize durable work by type. Prefer plain files, Git, and small reversible
changes. Keep the OS core small; extend through skills and project templates,
adding infrastructure only when an observed local need justifies it.

## Execution contract

- Match the request: answers and reviews inspect and report without changing
  scoped artifacts unless requested; diagnosis finds causes; change requests
  include implementation and proportionate validation.
- Continue authorized, safe local work without routine confirmation. Ask only
  for a necessary user choice or destructive, external, protected-data,
  substantial-cost, or scope-expanding actions not already authorized.
- The human owns research direction, consequential choices, publication, and
  final acceptance. Agent verification is part of delivery.
- Repository evidence outranks summaries and handoffs. Re-check facts that
  determine the next action; link to authorities instead of copying state.
- Finish when the requested outcome exists and relevant checks pass; report
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add pengqianhan/ai-human-research-os/AGENTS.md@sha256:5bd078d7a94883e8

The line at the top of this page pins the label git:20260930.4bad615, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_ajwatxfknwhehuo4.svg)](https://markdownregistry.com/a/art_ajwatxfknwhehuo4)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 23, 2026 and Sep 30, 2026, about one every 2 days.

version	committed	commit	size	audit
git:20260930.4bad615 latest	2026-09-30	4bad615	6,988 B	A	view · diff
git:20260929.a50a273	2026-09-29	a50a273	6,883 B	A	view · diff
git:20260928.c3acde4	2026-09-28	c3acde4	6,647 B	A	view · diff
git:20260927.c4d4a85	2026-09-27	c4d4a85	6,633 B	A	view · diff
git:20260923.7d7648b	2026-09-23	7d7648b	6,480 B	A	view

Audit of the latest version

A 14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Size between 200 bytes and 200 KB (6988 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

pengqianhan/ai-human-research-os · 3 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ajwatxfknwhehuo4
GET https://markdownregistry.com/api/v1/resolve?ref=pengqianhan/ai-human-research-os/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/5bd078d7a94883e8e08331191de6c7c85dd29b90cbc919a8eaccbab333c0e1da

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from pengqianhan/ai-human-research-os

DESIGN.md@os-ui DESIGN.md file

pengqianhan/ai-human-research-os · os-ui/DESIGN.md

git:20261010.e6ff292 · audit A · 3 stars

DESIGN.md@os-ui/client DESIGN.md file

pengqianhan/ai-human-research-os · os-ui/client/DESIGN.md

git:20261010.365f7eb · audit B · 3 stars

AGENTS.md@projects-folder/nanochat_cpu AGENTS.md file

pengqianhan/ai-human-research-os · projects-folder/nanochat_cpu/AGENTS.md

git:20260928.63ead0b · audit A · 3 stars

AGENTS.md@projects-folder/templates/ai_research_template AGENTS.md file

pengqianhan/ai-human-research-os · projects-folder/templates/ai_research_template/AGENTS.md

git:20260928.c3acde4 · audit A · 3 stars

algorithmic-art SKILL.md skill

pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/algorithmic-art/SKILL.md · Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users…

git:20260715.38d79be · audit B · 3 stars

alphafold2 SKILL.md skill

pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/alphafold2/SKILL.md · Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022…