MASA AGENTS.md

Repository instructions for MASA, a protocol and toolkit for describing sound, evidence, operations, policies, and their relationships. They define which files and tests are authoritative and which rules developers must preserve.

In plain words
What is it for?
They guide development, testing, and commits in the MASA repository, including how to handle records, transformations, unknown states, extensions, and generated code.
Why use it?
They give coding agents a shared contract for making changes without losing provenance, policy checks, or distinctions between different kinds of information.

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/prismatic7/masa/agents-md
Clone the repo
git clone --depth 1 https://github.com/prismatic7/MASA

Made for: Codex, OpenCode.

Per session 430 This file is loaded in full into every session.
When invoked 430 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 $0.00430 $0.00430
Opus 5 $0.00215 $0.00215
Sonnet 5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured yesterday against content hash 90fe1b297a70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

MASA 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 yesterday.

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 · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MASA repository contract

This repository contains the normative MASA Sound Matter Aware protocol and its local reference tooling.

Authority order

  1. Versioned files under spec/ define normative behavior.
  2. Versioned JSON Schema files under schemas/ define normative structure.
  3. Versioned registries under ontology/ define controlled vocabulary and relation metadata.
  4. Conformance fixtures and tests define executable expectations.
  5. TypeScript declarations and libraries are generated or implemented conveniences. They never override the language-neutral artifacts.

Invariants

  • Preserve source, representation, claim, operation, policy, and lineage as distinct objects.
  • Keep claim kind, actor, confidence, source health, freshness, and disclosure separate.
  • Keep unknown, withheld, unavailable, deleted, and not-applicable states distinct.
  • Never mutate or replace an imported representation under the same identifier after consequential transformation.
  • Every descendant has a parent relation and an operation receipt.
  • Every consequential operation has a policy evaluation, including refusal and non-action.
  • Unknown namespaced extensions survive ordinary local round trips. They are excluded from public projections unless explicitly approved.
  • Validation is offline. Validators and the MCP server do not dereference remote resources.
  • Public export is allowlist-based and creates a new projection. It never sanitizes a private record in place.
  • The reference implementation performs no digital signal processing. Processing operations are contracted to external engines and accounted through receipts.
  • Do not describe a profile, class, adapter, or integration as conformant without a recorded passing suite.

Development

Use Node.js 22.20 or newer and pnpm 10.32.1. Run pnpm check before calling the local reference implementation complete. Tests must use isolated temporary directories and may not write into sibling repositories.

Do not add an application-specific term to the masa: namespace until at least two implementations justify the promotion and a versioned decision records it. Concrete applications keep their own extension namespaces in their own repositories.

Read the full file on GitHub · 34 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. yesterday First seen · 34 lines · 430 tokens per session scan A 90fe1b297a70

Subscribe to this mod's changes

MASA AGENTS.md is an instructions file published in the GitHub repository prismatic7/MASA (0 stars, last pushed 13d ago), licensed MIT. It adds 430 tokens to every session, about $0.0022 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.

Related

Other instructions, from other repositories

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

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

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

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

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

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