awesome-claude-code-codex-papers AGENTS.md

Repository instructions for maintaining a catalogue of research papers about coding agents and related tools. They define which files are authoritative, how evidence should be recorded, and which checks to run.

In plain words
What is it for?
Use them when editing the paper catalogue, schema, taxonomy, or generated website data. They also specify the build and validation commands needed after changes.
Why use it?
They prevent edits to generated files from being lost and help keep paper claims, product relationships, and evaluation results accurately separated.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/micromilo/awesome-claude-code-codex-papers/agents-md
Clone the repo
git clone --depth 1 https://github.com/MicroMilo/awesome-claude-code-codex-papers

Made for: Codex, OpenCode.

Per session 244 This file is loaded in full into every session.
When invoked 244 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00244 $0.00244
Opus 5 $0.00122 $0.00122
Sonnet 5 $0.00049 $0.00049
Haiku 4.5 $0.00024 $0.00024

Measured 2d ago against content hash d254039cd373, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

awesome-claude-code-codex-papers 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 2d 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.

AGENTS.md · 29 lines

What it actually says

Repository instructions

Source of truth

  • Edit data/papers.yaml; do not hand-edit generated README stats, data/papers.json, website/data/catalog.json, papers/*.md, or views/*.md.
  • Update data/schema.json and docs/taxonomy.md together when adding fields, products, statuses, or method tags.
  • A product mention means the complete agent or harness, not merely a model from the same vendor.

Evidence rules

  • Prefer official proceedings, DOI, OpenReview, arXiv, and author-maintained artifacts.
  • Record paper claims as claims; do not silently convert them into universal conclusions.
  • Use unknown when model or budget parity is not established.
  • Keep direct, related, evaluation-only, and historical entries separate.
  • Never commit paper PDFs.

Commands

python -m pip install -r requirements-dev.txt
make build
make check
npm --prefix website install
make site-check

Run make build after catalog edits and include all generated changes in the same commit. The website reads the generated website/data/catalog.json; never maintain a second paper list in the frontend.

Changes

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.

  1. 2d ago First seen · 29 lines · 244 tokens per session scan A d254039cd373

Subscribe to this mod's changes

awesome-claude-code-codex-papers AGENTS.md is an instructions file published in the GitHub repository MicroMilo/awesome-claude-code-codex-papers (2 stars, last pushed 8d ago), licensed MIT. It adds 244 tokens to every session, about $0.0012 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 2026-08-31.

Related

Other instructions, from other repositories