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/opensecretcloud/maple/agents-mdgit clone --depth 1 https://github.com/OpenSecretCloud/MapleWhat 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 | $0.03485 | $0.03485 |
| Opus 5 | $0.01742 | $0.01742 |
| Sonnet 5 | $0.00697 | $0.00697 |
| Haiku 4.5 | $0.00348 | $0.00348 |
Grade A, and why
Maple 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 2d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maple agent guide
This file applies to the entire repository. It defines the durable rules an
agent should know before changing Maple. Task-specific procedures live under
.agents/skills/; load the matching skill before doing that work.
Start here
- Confirm the checkout, branch, and worktree state. Preserve unrelated user changes and do not switch branches or rewrite history in a dirty checkout.
- Read the relevant source and tests before proposing placement. Do not treat historical design documents as stronger evidence than current code.
- Before creating configuration or starting or stopping services, determine whether an external development environment owns this checkout's ignored environment files, local Tauri overlay, ports, or processes. Preserve those resources and follow that environment's lifecycle instructions. Standalone setup and startup examples apply only when no external orchestrator owns the affected resource.
- Enter the pinned environment with
nix develop. Install dependencies withjust installand enable the repository hook with./setup-hooks.sh. - If
frontend/.env.localis absent, create it withtest -e frontend/.env.local || cp frontend/.env.example frontend/.env.local. Never overwrite an existing file: it may be externally managed or contain checkout-specific backend and application configuration. Record the selected OpenSecret, feature-flags, and billing endpoints in smoke-test evidence; never put secrets inVITE_*variables. - Choose the runtime you actually need:
just devis web-only;just desktop-devis the Tauri application and is required for Agent Mode and other native behavior.
Product and runtime map
Maple is a React/Vite application packaged with Tauri for desktop and mobile. OpenSecret is its required backend. Keep these runtime paths distinct:
- Research chat: React -> OpenAI JavaScript client ->
@opensecret/reactencrypted custom fetch -> OpenSecret Responses and Conversations APIs. - Desktop Agent Mode: React -> Maple-owned Tauri commands/events ->
MapleAgentService-> embedded pinned Goose ->MapleProvider-> Rust OpenSecret SDK ->/v1/chat/completions. - ACP: an external client edge over a protected local socket into the same Maple Agent service. ACP is not Agent Mode's internal abstraction.
- Local proxy: a separate user-facing OpenAI-compatible relay. Research chat and Agent Mode do not internally route through it.
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.
- 2d ago First seen · 294 lines · 3,485 tokens per session scan A d05ffaeb05f7
Maple AGENTS.md is an instructions file published in the GitHub repository OpenSecretCloud/Maple (91 stars, last pushed 2d ago), licensed MIT. It adds 3,485 tokens to every session, about $0.0174 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.