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.
curl -O https://raw.githubusercontent.com/manusco/resonance/main/AGENTS.mdgit clone --depth 1 https://github.com/manusco/resonanceWrote 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/manusco/resonance/agents-md)<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>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 | $0.03783 | $0.03783 |
| Opus 5 | $0.01892 | $0.01892 |
| Sonnet 5 | $0.00757 | $0.00757 |
| Haiku 4.5 | $0.00378 | $0.00378 |
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.
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.
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.
- 3d ago First seen · 150 lines · 3,783 tokens per session scan A 0077ddab64d0
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.
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.
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.
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).
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).
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.
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.