Magnitude is an open-source inference server, meaning software that runs language models and answers requests on a user's own computer. It profiles available hardware, recommends suitable local models, and connects them to coding agents for private and offline use on macOS, Linux, or Windows through WSL. Its catalogue entries help agents set up and use Magnitude.
Borrowing it
Nothing to install: this file belongs to magnitudedev/magnitude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/magnitudedev/magnitude/main/AGENTS.mdgit clone --depth 1 https://github.com/magnitudedev/magnitudeWrote 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/magnitudedev/magnitude/agents-md)<a href="https://agentmods.dev/instructions/magnitudedev/magnitude/agents-md"><img src="https://agentmods.dev/badge/instructions/magnitudedev/magnitude/agents-md/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.
<a href="https://agentmods.dev/instructions/magnitudedev/magnitude/agents-md"><img src="https://agentmods.dev/badge/instructions/magnitudedev/magnitude/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02273 | $0.02273 |
| Opus 5.5 | $0.00909 | $0.00909 |
| Sonnet 5.5 | $0.00455 | $0.00455 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade A, and why
magnitude 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 today.
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.
Motel is a local OpenTelemetry collector with an HTTP API at `http://127.0.0.1:27686`. Query it with `curl` to inspect traces, spans, and logs from the application. How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TRESTING
Magnitude Project Context
You are working on Magnitude, an AI coding agent platform.
Package Layering
clients (cli/web) → client-common → sdk → acn (daemon)
- Clients import only from
@magnitudedev/client-commonand@magnitudedev/sdk. Never fromacn,agent,acn-protocol,ai, orprovidersdirectly. - client-common — shared state, hooks, display sync. Uses one connection-scoped Effect Query
AgentClientover the shared SDK instance. - sdk — private, portable Effect RPC client, fixed-endpoint admission/recovery, and optional service-starter capability. Re-exports pure protocol contracts; no SQLite, process supervision, or query cache.
- daemon-management — private desktop discovery/control, native child supervision, login registration. Only privileged host composition roots (CLI bootstrap, desktop main, development server) import it. The desktop bundles and owns ACN; clients never acquire or elect a standalone daemon.
- client-common owns first-party Query/Mutation/Subscription definitions over SDK operations;
providersowns provider-client construction. - acn — server daemon hosting agent runtime, sessions, file ops, display streams. Implements ACN protocol RPCs.
- acn-protocol — wire contract (RPCs, schemas) shared by SDK and ACN. Not imported by clients.
- ai — provider-agnostic contract (
Provider,ModelCatalog,BoundModel,BaseCallOptions). - providers — concrete provider implementations + registry. See
packages/providers/AGENTS.md. - agent — agent runtime, projections, workers, tools, display materialization.
- event-core — event sourcing, projections, addressed state.
- roles — role/slot definitions for worker specialization.
- storage — persistent session/config/auth storage.
For a new backend operation, declare its Rpc.make once in the appropriate packages/acn-protocol/src/boundary/ domain, implement its handler in ACN, and consume the derived SDK method. Add first-party caching/synchronization policy in packages/client-common/src/operations/ as needed. Effect Query does not generate RPCs. The SDK may ask an injected starter to ensure availability; only daemon-management owns native application control. Plugin packages bundle the private SDK and inherit its exact RPC-version check.
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.
- today Changed · +10 lines · +431 tokens per session 6688f229df32
- 2d ago Changed · -13 lines · -146 tokens per session 70053cdd0b3e
- 12d ago Changed · +4 lines · +73 tokens per session 00eacd9327fc
- 26d ago Changed · -1 tokens per session a774e56bfa83
- 1mo ago Changed · +13 tokens per session f5e6e271e5ad
- 1mo ago Changed · +6 lines · +148 tokens per session e37380deb17c
- 1mo ago First seen · 149 lines · 1,755 tokens per session scan A 15c2894e8e85
magnitude AGENTS.md is an instructions file published in the GitHub repository magnitudedev/magnitude (7,308 stars, last pushed today), licensed Apache-2.0. It adds 2,273 tokens to every session, about $0.0091 per session on Opus 5.5. 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 2026-08-30.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).