AutoSage AGENTS.md

AutoSage AGENTS.md is an instructions file for Codex, OpenCode from SeattleUser0/AutoSage. It costs 619 tokens per session, scanned A, original, MIT.

A project instruction file for AutoSage, a Swift toolkit that lets AI agents call science and engineering solvers through an OpenAI-compatible web interface. It describes the server, shared library, supported endpoints, and tool system.

In plain words
What is it for?
Use it when developing AutoSage’s Swift package, HTTP server, health check, response endpoints, or solver tool integrations.
Why use it?
It records the project’s fixed interfaces and engineering constraints so changes remain compatible and predictable.

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/seattleuser0/autosage/agents-md
Clone the repo
git clone --depth 1 https://github.com/SeattleUser0/AutoSage

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.

agentmods badge for AutoSage AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/seattleuser0/autosage/agents-md.svg)](https://agentmods.dev/instructions/seattleuser0/autosage/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/seattleuser0/autosage/agents-md"><img src="https://agentmods.dev/badge/instructions/seattleuser0/autosage/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 619 This file is loaded in full into every session.
When invoked 619 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00619 $0.00619
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured 3d ago against content hash 3b4d2cdac92b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AutoSage AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- curl examples for `/healthz`, `/v1/responses`, `/v1/chat/completions`
AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoSage — Agent Instructions

AutoSage is a backend toolkit that exposes an OpenAI-compatible HTTP interface so an AI agent (e.g., Open Claw) can run science/engineering solvers (FEA/CFD/circuits) through tool calls.

Non-negotiables

  • Repository license: MIT.
  • Only allow permissive third-party licenses in-tree: MIT, BSD-2/3, Apache-2.0, ISC, zlib.
  • Do not add GPL/LGPL/AGPL dependencies or code.
  • Must build cleanly via Swift Package Manager and open/build in Xcode.

Architecture

  • Swift Package with these targets:
    • AutoSageCore (library): shared types and tool system.
    • AutoSageServer (executable): HTTP server.
  • Keep solver implementations behind a narrow interface so they can be swapped/refactored later.
  • All externally visible behavior must be deterministic and size-bounded.

HTTP API (compatibility surface)

Implement and keep stable:

  • GET /healthz → 200 with minimal JSON (status/version)
  • POST /v1/responses → OpenAI Responses-like JSON
  • POST /v1/chat/completions → Chat Completions-like JSON

Defaults:

  • Bind to 127.0.0.1:8080 unless configured otherwise.
  • Content-Type application/json.

Tool system

AutoSage supports tool calls. Provide a registry that maps tool name → implementation.

Initial tools (stubs are OK):

  • fea.solve
  • cfd.solve
  • circuits.simulate

Tool contract:

  • Each tool has: name, description, jsonSchema (parameters), run(input) -> output.
  • Tool outputs must include:
    • status (e.g., "ok" / "error")
    • solver (string identifier)
    • summary (short human-readable)
    • Optional arrays must be capped/truncated (never return huge payloads).

Testing requirements

  • Add unit tests for JSON decoding/encoding of request/response types.
  • Add at least one handler smoke test per endpoint (request in → response shape out).
  • swift test must pass.

Docs and notices

  • Add README.md with:
    • how to build/run the server
    • curl examples for /healthz, /v1/responses, /v1/chat/completions
    • tool-call example for one tool
  • Add THIRD_PARTY_NOTICES.md (even if empty initially).
  • If any third-party code is added later, its license text must be included and referenced.

Read the full file on GitHub · 62 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 · 62 lines · 619 tokens per session scan A 3b4d2cdac92b

Subscribe to this mod's changes

AutoSage AGENTS.md is an instructions file published in the GitHub repository SeattleUser0/AutoSage (2 stars, last pushed 6mo ago), licensed MIT. It adds 619 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.