What is Open-Claude-Code AGENTS.md?

A project instruction guide for Open Claude Code, an open-source coding-agent application. It describes the codebase structure, security boundaries, verification practices, and repository rules.

Use it when modifying or reviewing the Open Claude Code repository, especially its agent loop, CLI, tools, middleware, providers, sessions, or tests.

It gives contributors the project-specific rules needed to change the code safely. It also shows where related runtime, tool, middleware, provider, session, and test code belongs.

How NastyRunner13/Open-Claude-Code configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to NastyRunner13/Open-Claude-Code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/NastyRunner13/Open-Claude-Code/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/NastyRunner13/Open-Claude-Code

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nastyrunner13/open-claude-code/agents-md/github.svg)](https://agentmods.dev/instructions/nastyrunner13/open-claude-code/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nastyrunner13/open-claude-code/agents-md"><img src="https://agentmods.dev/badge/instructions/nastyrunner13/open-claude-code/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nastyrunner13/open-claude-code/agents-md"><img src="https://agentmods.dev/badge/instructions/nastyrunner13/open-claude-code/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 656 This file is loaded in full into every session.

When invoked 656 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00656	$0.00656
Opus 5.5	$0.00262	$0.00262
Sonnet 5.5	$0.00131	$0.00131
Haiku 4.5	$0.00066	$0.00066

Measured 2mo ago against content hash 2b139ceb25ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Open-Claude-Code 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 2mo 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding-agent guide for Open Claude Code

Project map

src/open_claude_code/agent.py owns the provider/tool loop, authorization, streaming-event consumption, and session recording. Keep it UI-independent.
src/open_claude_code/main.py owns CLI parsing, terminal behavior, middleware construction, and non-interactive occ exec behavior.
src/open_claude_code/tools/ contains built-in tool schemas and their implementations. Runtime tools are bound in tools/__init__.py.
src/open_claude_code/middleware/ owns optional capabilities and lifecycle integration; preserve the ordering in main.py unless a change requires it.
src/open_claude_code/providers/ normalizes provider responses and streams.
src/open_claude_code/sessions/, subagents/, skills/, and mcp/ own their corresponding persistent or extension boundaries.
tests/ mirrors these areas. Add regression tests beside the closest existing test module.

Working rules

Preserve the security boundary. Built-in filesystem, shell, and web tools must receive and honor ToolContext; do not bypass it by calling raw paths, subprocesses, or HTTP clients from a tool implementation.
Enforce capabilities before approval. ToolPolicy and tool-local checks are non-bypassable; approval prompts only decide among policy-permitted calls.
Keep provider-specific code in providers/. The agent loop should consume normalized ProviderResponse and stream events only.
Return ToolResult from tools, including failures, with useful metadata. Preserve output truncation and report denied operations through ToolDenied.
Make edits reversible. Write, edit, multi-edit, and patch changes should use snapshots and return a unified diff when applicable.
Treat sessions as an append-only audit trail. Do not write credentials to session metadata or events; use the existing redaction path.
Keep compatibility with Python 3.12+, use type annotations, and avoid new runtime dependencies unless the feature needs them.

Read the full file on GitHub · 69 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.

2mo ago First seen · 69 lines · 656 tokens per session scan A 2b139ceb25ab

Subscribe to this mod's changes

Open-Claude-Code AGENTS.md is an instructions file published in the GitHub repository NastyRunner13/Open-Claude-Code (2 stars, last pushed 1mo ago), licensed MIT. It adds 656 tokens to every session, about $0.0026 per session on Opus 5.5. 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.

Open-Claude-Code AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Open-Claude-Code AGENTS.mdNastyRunner13/Open-Claude-Code	Instructions file	2	1mo ago	MIT	A	656	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

Open-Claude-Code: Instructions file for Codex