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/animicaorg/all/copilot-instructionsgit clone --depth 1 https://github.com/animicaorg/allWhat 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 | $0.02351 | $0.02351 |
| Opus 5 | $0.01175 | $0.01175 |
| Sonnet 5 | $0.00470 | $0.00470 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
all 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 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for Animica
This is a monorepo hosting a blockchain (PoIES consensus), execution layer (Python-VM), crypto infrastructure, SDKs (Python/TypeScript/Rust), and multiple UIs. Use this guide to navigate code patterns and workflows quickly.
Architecture Overview
Core layers:
- Consensus (
consensus/) — PoIES (Proof-of-Integrated-External-Services) accepts blocks using a deterministic score combining hash-share work + external proofs (AI, Quantum, Storage). Uses fixed-point μ-nats math, nullifier windows, and EMA-based difficulty retargeting. - Execution (
execution/) — Deterministic state machine running Python-VM contracts. Canonical CBOR I/O, gas metering, journaled state, and deterministic receipts. No side effects; pure functions. - Capabilities (
capabilities/) — Off-chain compute coordination for AI/Quantum jobs. Integrates with AICF (aicf/), which matches jobs to providers, settles payments, and enforces SLAs. - Contracts (
contracts/) — User-written Python contracts compiled to IR, deployed on-chain, and invoked via standardized ABIs. - SDKs (
sdk/) — Multi-language clients (Pythonomni_sdk, TypeScript@animica/sdk, Rustanimica-sdk) for RPC, tx building, wallet, and contract interaction.
Integration:
Contracts (Python-VM) ──enqueue AI/Quantum──> AICF ──assign──> Providers
▲ │ │
│ PoIES proofs execute
└──Receipts(on-chain) <─ Proofs ◀─ Providers publish ────────┘
Key Patterns
Determinism & Canonical Encoding
- All consensus paths must be pure (no network I/O, no clock). Randomness is seeded from chain data.
- CBOR canonical: sorted keys, minimal int encoding. See
spec/for schemas (params.yaml, poies_policy.yaml, abi.schema.json, manifest.schema.json). - Fixed-point math: logs in μ-nats (micro-nats,
int64). Seeconsensus/math.pyfor safe arithmetic with rounding rules documented. - Gas: deterministic per-opcode costs in
vm_py/gas_table.json; metering inexecution/gas/.
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 · 174 lines · 2,351 tokens per session scan A c98efc4bd6e4
all copilot-instructions.md is an instructions file published in the GitHub repository animicaorg/all (4 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2,351 tokens to every session, about $0.0118 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
Get-Started-with-Web3 AGENTS.md
Instructions for beihaili/Get-Started-with-Web3, covering get started with web3 agent notes, 项目定位, ceo 运营目标, 常用命令 and ai-native 内容层.
apex AGENTS.md
Instructions for macrocosm-os/apex, covering apex - bittensor subnet 1, what "mining apex" actually means, the few terms you can't avoid, step 1 — install the tools and download the apex code.
ethereum-wallet-toolkit AGENTS.md
AGENTS.md instructions for nirholas/ethereum-wallet-toolkit, covering ethereum-wallet-toolkit development guidelines, project overview, terminal management and contributing.
ethereum-wallet-toolkit copilot-instructions.md
Copilot instructions for nirholas/ethereum-wallet-toolkit, covering ethereum-wallet-toolkit and terminal management.
ethereum-wallet-toolkit GEMINI.md
Gemini CLI instructions for nirholas/ethereum-wallet-toolkit, covering ethereum-wallet-toolkit and terminal management.
tron_mcp_server CLAUDE.md
Claude Code instructions for Netts-official/tron_mcp_server, covering claude.md template for tron mcp server integration, what is claude.md?, basic template, project name and tron integration.