nautex AGENTS.md

A repository guide for Nautex open-source gateway tooling, which connects coding agents to the Nautex backend through a command-line tool, MCP server, and ACP bridge. ACP is a protocol for connecting agent clients with agent services.

In plain words
What is it for?
Use it when changing agent adapters, Nautex configuration, gateway protocols, or probe scripts. It also directs contributors to compatibility, credential-sandboxing, synchronization, and verification guidance.
Why use it?
It shows where the gateway, agent adapters, configuration generation, protocol files, and verification scripts live, helping agents follow the correct integration and testing path.

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/hmldns/nautex/agents-md
Clone the repo
git clone --depth 1 https://github.com/hmldns/nautex

Made for: Codex, OpenCode.

Per session 688 This file is loaded in full into every session.
When invoked 688 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 $0.00688 $0.00688
Opus 5 $0.00344 $0.00344
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 3d ago against content hash a09ab1a430f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nautex 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 3d 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents working in this repository.

What this project is

nautex-oss-util is the Nautex open-source gateway node and MCP tooling. It hosts a single ACP-to-Nautex bridge (nautex gateway) plus the CLI and MCP server used by coding agents to talk to the Nautex backend. The hot code path is under src/nautex/gateway/.

Where to look

  • src/nautex/gateway/adapters/ — one concrete adapter (ACPAgentAdapter) plus per-agent subclasses for Claude Code, OpenCode, Codex, and others. See src/nautex/gateway/adapters/AGENTS.md for the per-agent compatibility matrix, credential sandboxing rules, and integration effort logs.
  • src/nautex/gateway/adapters/launch_config.py — persistent config-file generation under ~/.nautex/configs/ with deterministic fingerprints.
  • src/nautex/gateway/protocol/ — synced with nt-backend via make sync-agw-protocol. Edit here, then sync.
  • scripts/ — the session-config probe and legacy raw-ACP probes. See scripts/AGENTS.md for the verification workflow (how and when to run the probe, how to read artifacts, when to add new scenarios).

Verification

The primary verification tool is the session-config probe. Full guide in scripts/AGENTS.md. Quick reference:

target when command
Session-config probe — single case mid-iteration, fastest feedback make session-config-probe ARGS='--agent X --scenario Y'
Session-config probe — full matrix before opening a PR that touches adapters or protocol make session-config-probe ARGS='--all --timeout 90'
ACP bridge + native binaries install check after environment changes make install-acp-adapters
Raw-ACP probe (new agent characterization only) adding a new agent python scripts/probe_acp_agents.py <agent_id>
Subsystem unit tests when touching a specific subsystem pytest tests/gateway/test_<subsystem>.py

Read the full file on GitHub · 59 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. 3d ago First seen · 59 lines · 688 tokens per session scan A a09ab1a430f6

Subscribe to this mod's changes

nautex AGENTS.md is an instructions file published in the GitHub repository hmldns/nautex (84 stars, last pushed 1mo ago), licensed MIT. It adds 688 tokens to every session, about $0.0034 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.