agentmods.dev

agent CLAUDE.md

A set of project instructions that routes every user message through a tool called JINX. JINX is started and continued by running a local Python script and exchanging YAML request and response files.

In plain words
What is it for?
Use it in projects that require every request to pass through JINX, including generated answers and tool-call execution. The input does not describe JINX's underlying capabilities.
Why use it?
It centralizes how an agent handles messages and tool calls, instead of allowing the agent to respond or act directly.

Instructions file

281 12d ago A scan 205 tokens original Apache-2.0
View the source file machinegpt/agent
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/machinegpt/agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/machinegpt/agent
Per session 205 This file is loaded in full into every session.
When invoked 205 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 $0.00205 $0.00205
Opus 5 $0.00102 $0.00102
Sonnet 5 $0.00041 $0.00041
Haiku 4.5 $0.00020 $0.00020

Measured 2d ago against content hash 53626a79b8c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent 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 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.

CLAUDE.md · 11 lines

What it actually says

Project Rules

ALWAYS route absolutely every single user message, greeting, or task through JINX. Do not reply directly or perform any actions yourself.

  1. Start JINX: Run python .agent/jinx.py "[user_message]" (first time) or python .agent/jinx.py (to resume).
  2. Loop JINX: If .agent/jinx_request.yaml is created:
    • "llm_generate": Generate completion using YAML's system/messages/tools. Write {"content": content_blocks} to .agent/jinx_response.yaml (encoded in YAML format).
    • "tool_calls": Execute YAML's tool calls. Write {"results": [{"tool_use_id": "id", "content": "output"}]} to .agent/jinx_response.yaml (encoded in YAML format).
    • Re-run python .agent/jinx.py and repeat the loop until .agent/jinx_request.yaml is gone.
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 · 11 lines · 205 tokens per session scan A 53626a79b8c0

Subscribe to this mod's changes

agent CLAUDE.md is an instructions file published in the GitHub repository machinegpt/agent (281 stars, last pushed 12d ago), licensed Apache-2.0. It adds 205 tokens to every session, about $0.0010 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.

LanguagesPlanning
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens