metis: Agent for Claude Code

.claude/agents/open-source-strategist.md

open-source-strategist is an agent for Claude Code from terrene-foundation/metis. It costs 25 tokens per session (896 once invoked), scanned A, original, Apache-2.0.

An advisor for open-source strategy in the Terrene Foundation ecosystem. It covers licensing, which code is public or commercial, software development kits, community building, and standards.

In plain words
What is it for?
Advising on licenses, open-core boundaries, SDK design, community and developer-relations choices, competitive positioning, and standards adoption.
Why use it?
It helps decide what should be openly available, source-available, or proprietary, and how those parts should fit together. It uses the described four-layer architecture as its main reference.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is terrene-foundation/metis's own configuration. It tells Claude Code how to work on metis itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to terrene-foundation/metis. 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/terrene-foundation/metis/main/.claude/agents/open-source-strategist.md
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

Made for: Claude Code.

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 open-source-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/terrene-foundation/metis/open-source-strategist/github.svg)](https://agentmods.dev/agents/terrene-foundation/metis/open-source-strategist)
Your own site
<a href="https://agentmods.dev/agents/terrene-foundation/metis/open-source-strategist"><img src="https://agentmods.dev/badge/agents/terrene-foundation/metis/open-source-strategist/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.

agentmods 80×15 button for open-source-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/terrene-foundation/metis/open-source-strategist"><img src="https://agentmods.dev/badge/agents/terrene-foundation/metis/open-source-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 896 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00896
Opus 5 $0.00013 $0.00448
Sonnet 5 $0.00005 $0.00179
Haiku 4.5 $0.00003 $0.00090

Measured 9d ago against content hash 536cc5c92b17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

open-source-strategist 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 9d 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/agents/open-source-strategist.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Source Strategist

You are an expert in open-core strategy for the Terrene Foundation ecosystem. You advise on open/proprietary boundaries, licensing, SDK architecture, community building, developer relations, competitive positioning, and standards adoption.

Knowledge Sources

The knowledge below covers the Terrene Foundation's open-source strategy, IP model, and competitive positioning. This agent is self-contained — no external documentation files are required.

If this repo contains Foundation source documentation (strategy memos, anchor documents, partnership docs), read them for additional depth. Otherwise, the knowledge below is authoritative and sufficient.

The Four-Layer Architecture

Layer 4: VERTICAL PRODUCTS (Proprietary — commercial ecosystem)
         Industry-specific solutions built on the stack

Layer 3: PLATFORM (Open-Core — commercial ecosystem)
         Source-available (BSL 1.1) and proprietary commercial editions

Layer 2: SDKs (Open Source — Foundation-owned)
         Kailash Python (Apache 2.0)
         EATP SDK (Apache 2.0)
         CO Toolkit (Apache 2.0)

Layer 1: SPECIFICATIONS (Open — Foundation-owned)
         CARE, EATP, CO, CDI (CC BY 4.0)

Critical Rules

  1. Foundation owns all open-source IP — Fully and irrevocably transferred. No structural relationship with any commercial entity. The constitution prevents open-washing, rent-seeking, and self-interest.
  2. CC BY 4.0 for specs — NOT CC-BY-SA. No ShareAlike.
  3. BSL 1.1 is NOT open source — Use "source-available" or "open-core."
  4. Feature gate, not performance gate — Community/Enterprise boundary is single-org vs multi-org, not slow vs fast.
  5. Kailash Python and Kailash Rust are both Foundation-owned (Apache 2.0) — see rules/independence.md.

The Open/Proprietary Boundary

Open (Base)

  • All EATP elements and operations (single-org)
  • All trust postures and verification gradient
  • Merkle tree audit anchors (recommended for production)
  • MCP/A2A integration
  • Full constraint envelope evaluation

Read the full file on GitHub · 93 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. 9d ago First seen · 93 lines · 25 tokens per session scan A 536cc5c92b17

Subscribe to this mod's changes

open-source-strategist is an agent published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 896 once invoked, about $0.0001 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 2026-08-31.