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/chazmaniandinkle/oscine/agents-mdgit clone --depth 1 https://github.com/chazmaniandinkle/oscineWrote 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/chazmaniandinkle/oscine/agents-md)<a href="https://agentmods.dev/instructions/chazmaniandinkle/oscine/agents-md"><img src="https://agentmods.dev/badge/instructions/chazmaniandinkle/oscine/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 | $0.01674 | $0.01674 |
| Opus 5 | $0.00837 | $0.00837 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
oscine 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents and humans working in the Oscine codebase. Oscine
is itself agent-controllable at runtime (MCP + OSC); this file is about
editing its source. Read README.md for what the app is, ROADMAP.md
for what's planned next (and what's already shipped), and
docs/landscape.md for the competitive research behind those calls.
The one rule that matters
The command catalog is the contract. Features land as catalog commands first, UI second.
src/api/commands.js is the single source of truth for every
programmatic capability. The MCP tools and the OSC address space are
derived from it, and the UI calls the same store actions the catalog
handlers do. If you add a feature to the UI without a corresponding
command, you have broken the project's core promise (UI/console/MCP/OSC
parity). Add the command, then wire the UI to it.
To add a command: define it in src/api/commands.js (name, description,
JSON Schema), implement cmd_<name> in src/api/api.js. It then surfaces
automatically as an oscine_<name> MCP tool and, if you add a route, in
plugin/server/osc-gateway.js. The smoke tests fail if a catalog command
has no handler.
Architecture invariants
Data flow is one-directional and event-driven. Do not shortcut it.
UI gesture / console / MCP / OSC
-> store action (the ONLY place project state mutates)
-> bus event
-> engine mirrors audio, UI re-renders
Layer boundaries, enforced by discipline (and partly by tests):
src/core/has no DOM and no audio. It must stay importable from node (the tests import it). Bus, store, schema, persistence, utils.src/engine/is audio only and never mutates the project. It reacts to bus events and mirrors state into Web Audio nodes.src/ui/is DOM only and never touches audio nodes directly; it calls store actions and reads state.src/api/is the programmatic surface (catalog + handlers + bridge).
The engine and UI never call each other. Both react to the store through the bus. This is what makes undo, load, and autosave fall out for free, and it's why the agent surface can exist at all.
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 · 145 lines · 1,674 tokens per session scan A 0647a713a6ff
oscine AGENTS.md is an instructions file published in the GitHub repository chazmaniandinkle/oscine (0 stars, last pushed 21d ago), licensed MIT. It adds 1,674 tokens to every session, about $0.0084 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
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).
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.
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.
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.
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).
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.