agentleFS
Sign inStart free
XiaYiHannXiaYiHann/scholar-3/AGENTS.md

scholar-3

AGENTS.md0 starsChanged 9 months agoMITView on GitHub

This repository is a strict, spec-driven research workflow for agentic coding tools (Claude Code / Codex).

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository7 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No fabricated results: Never claim improvements, p-values, or empirical conclusions without pointers to actual artifacts.

    line 7
  2. Distinctive:

    Prefer multi-agent investigation for independent sub-tasks.

    line 12
  3. Distinctive:

    After an agent returns results, integrate them and close the agent.

    line 13
  4. Very specific:

    If research/idea.meta.yaml says state: frozen, do NOT edit research/idea.md directly.

    line 23
  5. Very specific:

    If experiments suggest changing formulation/protocol, create an Idea Amendment file: research/idea-amendments/Axx-*.md and request explicit …

    line 24
  6. Very specific:

    Keep YAML front matter valid in skills//SKILL.md and commands//COMMAND.md.

    line 29
  7. Distinctive:

    Keep README and README.zh-CN consistent about paths and commands.

    line 30
  8. Distinctive:

    Do not introduce new paths without updating:

    line 31
  9. Very specific:

    Every template path referenced by skills exists: scholar/schemas/scholar-research/templates/*

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Scholar-3 (OPSX-style Research) — AGENTS.md

This repository is a strict, spec-driven research workflow for agentic coding tools (Claude Code / Codex).

Non-negotiables (Truthfulness & Verifiability)

  • No fabricated citations. Title/author/year/venue/arXiv/DOI/URL must come from websearch results or user-provided materials. Otherwise mark as UNVERIFIED.
  • No fabricated results. Never claim improvements, p-values, or empirical conclusions without pointers to actual artifacts.
  • Evidence-first writing. Any paper claim must map to evidence pointers (tables/figures/logs/proofs).
  • If you don't know, say you don't know and request missing inputs. Do not "reasonable-guess" facts.

Agent coordination

  • Prefer multi-agent investigation for independent sub-tasks.
  • After an agent returns results, integrate them and close the agent.

Source of truth files (in the user's project, not this repo)

  • research/idea.md — single global Idea Spec (formulation + protocols + IDs)
  • research/idea.meta.yaml — state machine (draft/frozen), version, counters
  • research/evidence-ledger.md — Claim→Evidence→Pointer ledger (statuses)
  • research/proposals/Pxx-*/ — phase proposals with tasks and artifacts
  • research/paper/ — manuscript/rebuttal outputs

Idea freeze rule (critical)

  • If research/idea.meta.yaml says state: frozen, do NOT edit research/idea.md directly.
  • If experiments suggest changing formulation/protocol, create an Idea Amendment file: research/idea-amendments/Axx-*.md and request explicit user decision (accept/reject/defer).

Repo editing rules (when modifying THIS skill repo)

  • Keep YAML front matter valid in skills/**/SKILL.md and commands/**/COMMAND.md.
  • Keep README and README.zh-CN consistent about paths and commands.
  • Do not introduce new paths without updating:
    • settings.json.template
    • README docs
    • skills outputs list

Sanity checklist before finishing changes

  • settings.json.template points to real skill/command directories.
  • Every template path referenced by skills exists: scholar/schemas/scholar-research/templates/*
  • Commands/skills mention the same output paths.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free