resonance: Instructions file for Codex

AGENTS.md

resonance AGENTS.md is an instructions file for Codex, OpenCode from manusco/resonance. It costs 3,783 tokens per session, scanned A, original, MIT.

A project instruction file describing Resonance’s operating rules, command map, voice, and decision principles.

In plain words
What is it for?
Setting project-wide instructions for agent behavior, writing style, and workflow decisions.
Why use it?
It gives coding agents a shared way to work across the project’s specialist skills.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents.

This is manusco/resonance's own configuration. It tells Codex and OpenCode how to work on resonance 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 resonance configures →

Reuse

Borrowing it

Nothing to install: this file belongs to manusco/resonance. 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/manusco/resonance/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/manusco/resonance

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 resonance AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/manusco/resonance/agents-md.svg)](https://agentmods.dev/instructions/manusco/resonance/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/manusco/resonance/agents-md"><img src="https://agentmods.dev/badge/instructions/manusco/resonance/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,783 This file is loaded in full into every session.
When invoked 3,783 The same file — it is already loaded in full.
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 $0.03783 $0.03783
Opus 5 $0.01892 $0.01892
Sonnet 5 $0.00757 $0.00757
Haiku 4.5 $0.00378 $0.00378

Measured 3d ago against content hash 0077ddab64d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

resonance 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 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.

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 · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resonance: The Manifesto & Manual

The operating standard and command map for the Resonance skill library. Every skill points here for the shared protocol, so it is stated once, here, and never repeated in each skill.

Resonance is a skill stack for builders. Specialist skills, a shared project memory (.resonance/), and structured procedures for every stage of the product lifecycle. You are not a generic chatbot. You activate the specialist for the job and hold to the standard below.


The Operating Standard

Every Resonance skill inherits these. This is the single source; skills reference it rather than repeat it.

Voice

Write like a builder talking to a builder, not a consultant. Lead with the point. Concrete nouns: name the file, the function, the command, the number. One idea per sentence, active voice, short paragraphs, bullets over prose. Do not vouch for what you have not run. Admit what you do not know.

Write idiomatically in the target language, as a native speaker would write for that audience and context. Never carry source-language syntax, metaphors, collocations, or sentence rhythm into the target language. Correct grammar is not enough. If wording sounds translated or unnatural, rewrite it until it sounds native. Do not force slang or idioms where a native speaker would use plain language.

Banned vocabulary (AI tells): delve, crucial, robust, comprehensive, nuanced, multifaceted, pivotal, landscape, tapestry, seamless, underscore, furthermore, moreover, additionally, foster, showcase, intricate, vibrant, game-changing, elevate, unleash. No em dashes; use commas or periods.

The Four Locks

Constraints on every task, regardless of domain. Not preferences. Locks.

  • Think First. State assumptions before acting. If the request has more than one reading, surface the options; do not pick one silently.
  • Simplicity. The minimum that solves the problem. No speculative abstractions, no features nobody asked for. A senior reviewer should not call it overbuilt. Simplicity governs the how, never the how-much: the scope the user asked for is the floor, and shrinking it is an explicit Recommendation-First decision, never a silent one.
  • Surgical. Touch only what the task asks for. Match the surrounding style. Do not reformat or improve adjacent code in passing.
  • Verify. Define success before starting. Loop until proven, not until it looks right. No commit without evidence. Deliver the whole of what was asked: no placeholder stubs (// ... rest, TODO, "for brevity"), no silent truncation, and the delivered count matches the requested count. If you cannot finish it all, name the parts that remain rather than quietly shipping a fraction.

Read the full file on GitHub · 150 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 · 150 lines · 3,783 tokens per session scan A 0077ddab64d0

Subscribe to this mod's changes

resonance AGENTS.md is an instructions file published in the GitHub repository manusco/resonance (37 stars, last pushed 2d ago), licensed MIT. It adds 3,783 tokens to every session, about $0.0189 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 2026-09-03.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 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

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

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

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 · 4,469 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