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.
npx agentmods add instructions/thejavapirate/model-context-stream/agents-mdgit clone --depth 1 https://github.com/thejavapirate/model-context-streamWrote 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.
[](https://agentmods.dev/instructions/thejavapirate/model-context-stream/agents-md)<a href="https://agentmods.dev/instructions/thejavapirate/model-context-stream/agents-md"><img src="https://agentmods.dev/badge/instructions/thejavapirate/model-context-stream/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01965 | $0.01965 |
| Opus 5 | $0.00983 | $0.00983 |
| Sonnet 5 | $0.00393 | $0.00393 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade A, and why
model-context-stream 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working on model-context-stream
You are working on a living, event-driven MCP server: Redis-Streams-backed context streams,
a task queue with atomic claims, versioned protocols, MCP tool federation, outbound webhooks,
and agent presence — served over MCP Streamable HTTP so fleets of AI agents stay mutually
context-aware. Read README.md for the product story; this file is how to work on it.
Setup from a blank clone
npm install # Node >= 22 (testcontainers/undici require it; runtime image is node 22)
docker compose up -d redis # local Redis for `npm run dev`
npm run dev # tsx watch, http://localhost:3000
Docker must be running for tests (unit tests boot real Redis via testcontainers — mocks get XADD/XREAD/Lua semantics wrong and are deliberately not used).
Commands
| Command | What it does |
|---|---|
npm run typecheck |
tsc --noEmit — run after every change |
npm test |
Unit suites (test/unit/*) — real Redis per suite via testcontainers |
npm run test:e2e |
In-process end-to-end: 5-check smoke + federation vs a fake upstream |
npm run smoke |
Smoke an already-running server (MCS_URL, MCS_TOKEN env) |
docker compose up -d --build |
Full stack (server + Redis, AOF persistence) |
helm lint deploy/helm/model-context-stream |
Chart validation |
Definition of done for any nontrivial change: typecheck → npm test → npm run test:e2e →
docker compose up -d --build && MCS_URL=http://localhost:3000 MCS_TOKEN=<token> npm run smoke.
The smoke script is the executable definition of "the product works".
Every user-visible change adds a CHANGELOG.md entry under ## [Unreleased] (Added /
Changed / Fixed). Cutting a release = move that section under a new ## [X.Y.Z] — <date>
heading, bump package.json + deploy/helm/.../Chart.yaml (version and appVersion) + the
site's version eyebrow, commit, then git tag vX.Y.Z && git push origin vX.Y.Z — the tag
publishes the multi-arch image and chart to GHCR.
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.
- 4d ago First seen · 107 lines · 1,965 tokens per session scan A d8caa987c26c
model-context-stream AGENTS.md is an instructions file published in the GitHub repository thejavapirate/model-context-stream (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,965 tokens to every session, about $0.0098 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.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
toh-framework CLAUDE.md
Claude Code instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
hatch3r CLAUDE.md
Claude Code instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).