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/berkayoztunc/orquestra/copilot-instructionsgit clone --depth 1 https://github.com/berkayoztunc/orquestraWrote 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/berkayoztunc/orquestra/copilot-instructions)<a href="https://agentmods.dev/instructions/berkayoztunc/orquestra/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/berkayoztunc/orquestra/copilot-instructions.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 | $0.01321 | $0.01321 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
orquestra copilot-instructions.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 6d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions — orquestra
Project Overview
orquestra converts Solana Anchor IDLs into production-ready API. Users upload an IDL, and the platform auto-generates endpoints for every instruction, account type, and error — plus base58 transaction building and AI-ready Markdown docs.
Architecture
Monorepo (bun workspaces) with four packages:
| Package | Stack | Runs on | Purpose |
|---|---|---|---|
packages/worker/ |
Hono + TypeScript | Cloudflare Workers | API backend — auth, IDL parsing, tx building, doc generation |
packages/frontend/ |
React 18 + Tailwind + Vite | Cloudflare Pages | SPA dashboard — project management, explorer, API key mgmt |
packages/cli/ |
TypeScript + Bun | Local CLI | Program discovery and on-chain IDL availability checks |
packages/shared/ |
TypeScript | Shared | Canonical types (AnchorIDL, User, Project, etc.) and utilities |
Infrastructure: Cloudflare D1 (SQLite) for persistence (including ai_analyses, known_addresses, and FTS tables), KV namespaces (IDLS, CACHE) for fast IDL retrieval/caching, and Cloudflare Workers/Pages deployment via wrangler.toml.
Key Patterns & Conventions
Worker route structure
Each route file in packages/worker/src/routes/ creates its own new Hono<Env>() app and is mounted in packages/worker/src/index.ts via app.route(). The Env type defines Bindings (D1, KV, secrets) and Variables (auth context set by middleware).
Env/Bindings type — re-declared per file
The Env type with Bindings and Variables is re-declared locally in each route file rather than imported from a central location. Follow this pattern when adding new routes.
Auth flow
- JWT (Web Crypto API, no Node.js
crypto) viaservices/jwt.ts - Three middleware levels in
middleware/auth.ts:authMiddleware(required),optionalAuthMiddleware(silent pass-through),apiKeyMiddleware(X-API-Key header) - Auth context is set on Hono's
c.set('userId', ...)/c.get('userId')
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.
- 6d ago First seen · 102 lines · 1,321 tokens per session scan A d1a295d75052
orquestra copilot-instructions.md is an instructions file published in the GitHub repository berkayoztunc/orquestra (22 stars, last pushed 19d ago), licensed MIT. It adds 1,321 tokens to every session, about $0.0066 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
pumpfun-bonkfun-bot CLAUDE.md
Instructions for chainstacklabs/pumpfun-bonkfun-bot, covering agent guide, ground rules, layout, naming inside learning-examples/ and commands.
auditor-skill AGENTS.md
AGENTS.md instructions for solanabr/auditor-skill, covering auditor-skill — agent orchestration, flow (full audit) and trail of bits (vendored submodule).
x402-client AGENTS.md
Instructions for vybenetwork/x402-client, covering vybe x402 client — agent instructions, quick reference, prerequisites, complete flow and step 1: install.
solana-uiux-onboarding-kit CLAUDE.md
Instructions for draaujpeg/solana-uiux-onboarding-kit, covering solana ui/ux onboarding kit, language, where the truth lives, commands and always.
agenticpay CLAUDE.md
Claude Code instructions for agenticpay-dev/agenticpay, covering agenticpay, merge do main nie wdraża produkcji, brak sieci w /supported bywa poprawny and kody odrzucenia z @x402/svm wychodzą na drucie.
solana-vault-standard CLAUDE.md
Instructions for solanabr/solana-vault-standard, covering solana tokenized vault standard, communication style, branch workflow, mandatory workflow and security principles.