anolisa AGENTS.md

Repository instructions for Anolisa, a monorepo—one repository containing multiple related programs—for an operating layer built for AI agents.

In plain words
What is it for?
Use them when working on components such as the TypeScript shell, Rust services, security tools, memory system, or Linux-only modules.
Why use it?
They map the many components, their programming languages, and their supported systems so changes and commands target the correct part.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/alibaba/anolisa/agents-md
Clone the repo
git clone --depth 1 https://github.com/alibaba/anolisa

Made for: Codex, OpenCode.

Per session 5,082 This file is loaded in full into every session.
When invoked 5,082 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.05082 $0.05082
Opus 5 $0.02541 $0.02541
Sonnet 5 $0.01016 $0.01016
Haiku 4.5 $0.00508 $0.00508

Measured 2d ago against content hash 89e5fce47205, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anolisa 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.

AGENTS.md · 437 lines

How it starts

The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides context for AI coding assistants (Qoder, Claude, etc.) working in this repository.

1. Project Overview

ANOLISA is a monorepo for an Agentic OS — a server-side operating layer designed for AI agent workloads.

Component Path Tech Platform
copilot-shell (cosh) src/copilot-shell/ TypeScript / Node.js All
cosh-ng src/cosh-ng/ Rust Linux (full); macOS (limited functionality)
agent-sec-core src/agent-sec-core/ Rust + Python Linux only
agentsight src/agentsight/ Rust (eBPF) Linux (full); macOS (trajectory/serve only)
tokenless src/tokenless/ Rust Linux (full); macOS x64/arm64 (CLI binaries + adapters, via npm)
agent-memory (memory) src/agent-memory/ Rust Linux only
os-skills src/os-skills/ Python / Shell All
anolisa src/anolisa/ Rust Linux + macOS (arm64)
SkillFS (skillfs) src/skillfs/ Rust / FUSE Linux only
ws-ckpt src/ws-ckpt/ Rust + TypeScript Linux only
ktuner src/ktuner/ Rust Linux only
blaze src/blaze/ Rust Linux only

agent-sec-core, agent-memory, skillfs, ktuner, and blaze require Linux. agentsight provides full eBPF tracing on Linux and limited trajectory collection plus the local viewer on macOS. cosh-ng is Linux-first and supports limited functionality on macOS. Do not attempt to build the Linux-only components on macOS or Windows. (tokenless ships macOS CLI binaries and framework adapters via npm, but the binaries are cross-compiled from Linux — building tokenless on macOS is still unsupported.)

2. Development Commands

# Unified build (recommended — handles deps, build, and user install)
./scripts/build-all.sh                                        # integrated default components
./scripts/build-all.sh --no-install                           # build only, skip install
./scripts/build-all.sh --ignore-deps                          # skip dependency setup and runtime verification
./scripts/build-all.sh --component cosh --component sec-core  # selected components

# Partial convenience test runner (five components; may skip unavailable suites)
./tests/run-all-tests.sh
./tests/run-all-tests.sh --filter shell   # copilot-shell only
./tests/run-all-tests.sh --filter sec     # agent-sec-core only
./tests/run-all-tests.sh --filter sight   # agentsight only

# copilot-shell (per-component)
cd src/copilot-shell
make deps      # npm install + husky hooks (use make deps-ci in CI)
make build
make lint
make test

# cosh-ng (Linux full; macOS limited functionality, per-component)
cd src/cosh-ng
cargo build --workspace
cargo fmt --all -- --check
# Select the closest targeted test from src/cosh-ng/CONTRIBUTING.md.
# Full gates require a large/cross-cutting change and an explicit request.

# agent-sec-core (Linux only; Python 3.11.6 + uv, per-component)
cd src/agent-sec-core
make build-all
uv run --project agent-sec-cli python --version  # must report 3.11.6
make test         # Python + Rust sandbox + OpenClaw plugin tests

# agentsight (Linux full eBPF; macOS trajectory/serve only, per-component)
cd src/agentsight
# Linux
make build-all
make lint
make test

# macOS
make build-mac

# os-skills
cd src/os-skills   # Skill definitions are static assets, no compilation needed

# tokenless (per-component)
cd src/tokenless
make build       # tokenless + RTK + OpenClaw plugin
make lint
make test        # Rust + hooks + integration + adapters

# agent-memory (Linux only, per-component)
cd src/agent-memory
make build       # cargo build --release --locked
make fmt-check
make lint
make test        # cargo test --locked
make smoke       # end-to-end MCP stdio smoke test

# anolisa (per-component)
cd src/anolisa
cargo fmt --all --check
cargo clippy --all-targets --locked -- -D warnings
cargo test --locked

# ws-ckpt (Linux only, per-component)
cd src/ws-ckpt
make build       # cargo build --release + openclaw plugin
make test        # cargo test --workspace

# SkillFS (Linux only, per-component)
cd src/skillfs
cargo fmt --all --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace
scripts/test.sh   # FUSE smoke test; skips itself if fuse3 or /dev/fuse is unavailable

# ktuner (Linux only, per-component)
cd src/ktuner
cargo fmt --all --check
cargo clippy --all-targets -- -D warnings
cargo test

# blaze (Linux only, per-component)
cd src/blaze
cargo fmt --all --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace

Read the full file on GitHub · 437 lines

Changes

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.

  1. 2d ago First seen · 437 lines · 5,082 tokens per session scan A 89e5fce47205

Subscribe to this mod's changes

anolisa AGENTS.md is an instructions file published in the GitHub repository alibaba/anolisa (614 stars, last pushed 3d ago), licensed Apache-2.0. It adds 5,082 tokens to every session, about $0.0254 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.

Related

Other instructions, from other repositories