awesome-code-agents CLAUDE.md

awesome-code-agents CLAUDE.md is an instructions file for coding agents from EuniAI/awesome-code-agents. It costs 1,871 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for maintaining a curated catalogue of research papers about autonomous coding agents.

In plain words
What is it for?
Use it when editing the catalogue, its documentation, its data pipeline, or its automation files.
Why use it?
It gives contributors clear rules for where project information belongs, how files should be written, and how changes should be handled.

Instructions file

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/euniai/awesome-code-agents/claude-md
Clone the repo
git clone --depth 1 https://github.com/EuniAI/awesome-code-agents

Wrote 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.

agentmods badge for awesome-code-agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/euniai/awesome-code-agents/claude-md.svg)](https://agentmods.dev/instructions/euniai/awesome-code-agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/euniai/awesome-code-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/euniai/awesome-code-agents/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,871 This file is loaded in full into every session.
When invoked 1,871 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 $0.01871 $0.01871
Opus 5 $0.00936 $0.00936
Sonnet 5 $0.00374 $0.00374
Haiku 4.5 $0.00187 $0.00187

Measured 4d ago against content hash c52112903d70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

awesome-code-agents CLAUDE.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 4d 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.

CLAUDE.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Awesome Code Agents — Project Context

Working Preferences (owner: Zhaoyang-Chu)

  • Always work directly on main, no worktrees. Commit and push after each logical change so nothing gets lost.
  • Do NOT add Co-Authored-By: Claude to commit messages. Commits show only the owner's account.
  • English-only repo. Every file (data, docs, commit messages, comments) is English. No Chinese anywhere in the repo.
  • No em-dashes in anything we write (they read as AI-written). Use colons, commas, parentheses, or separate sentences. Never alter em-dashes inside a paper's own title or abstract (quoted source text).
  • Keep the design philosophy current in automation/DESIGN.md: it states the repo's final design and the reasoning behind it, organized by theme (no dated log, no superseded alternatives). When a turn settles a non-trivial design point, fold it into the right section that same turn. Chat is ephemeral; the repo is the memory.

What This Is

A curated list of research papers on autonomous code agents, published at euni.ai and github.com/EuniAI/awesome-code-agents. Rebuilt from the ground up in 2026-07 (taxonomy, data, and pipeline); the old system lives only in git history. Design rationale: automation/DESIGN.md; the rebuild-era records (legacy audit, completeness warrant) live at the git tag rebuild/2026-07.

The Two Sources of Truth

  • automation/data/taxonomy.json: the category system. Four top-level branches: foundation_models (flagship general models), studies (surveys and empirical research about the agents), artifact (code as the deliverable; 8 domains, software expands into 10 lifecycle activities), agency (code as the language of action; 6 worlds). Machine-facing contract per node: definition / includes / boundary / examples; plus a repo-wide scope with a hardened relevance gate and an ordered master_test. The classifier prompt is COMPILED from this file; never hand-write category text elsewhere.
  • automation/data/calibration.json: owner-labeled real papers as positive and negative few-shot examples (each with a why). They guide the classifier by precedent; they never pin papers by id. Grows automatically from review feedback (see the learning loop) and by hand when the owner rules on a case.

Read the full file on GitHub · 130 lines

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. 4d ago First seen · 130 lines · 1,871 tokens per session scan A c52112903d70

Subscribe to this mod's changes

awesome-code-agents CLAUDE.md is an instructions file published in the GitHub repository EuniAI/awesome-code-agents (127 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,871 tokens to every session, about $0.0094 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.

Related

Other instructions, from other repositories

LightRAG AGENTS.md

AGENTS.md instructions for HKUDS/LightRAG, covering repository guidelines, project overview, project structure, module layout (lightrag/) and core architecture.

HKUDS/LightRAG · 9,600 tokens

agentscope copilot-instructions.md

Copilot instructions for agentscope-ai/agentscope, covering agentscope code review guide, 1. code quality, 2. [must] code security, 3. [must] testing & dependencies and 4. code standards.

agentscope-ai/agentscope · 741 tokens

awesome-ChatGPT-repositories CLAUDE.md

Claude Code instructions for taishi-i/awesome-ChatGPT-repositories, covering awesome-chatgpt-repositories — claude code guide, repository structure, plugin skill (when installed via /plugin), local standalone command (when repo is cloned) and compact data format (plugins/awesome-chatgpt-search/data/).

taishi-i/awesome-ChatGPT-repositories · 995 tokens

PentestGPT CLAUDE.md

Instructions for GreyDGL/PentestGPT, covering claude guide, active project map, runtime contract, commands and documentation map.

GreyDGL/PentestGPT · 780 tokens

redis-vl-python CLAUDE.md

Claude Code instructions for redis/redis-vl-python, covering claude.md - redisvl project context, frequently used commands, development workflow, redis setup and documentation.

redis/redis-vl-python · 1,033 tokens

langfuse AGENTS.md

AGENTS.md instructions for langfuse/langfuse, a project described as: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23.

langfuse/langfuse · 6 tokens