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/tonycasey/lisa/agents-mdgit clone --depth 1 https://github.com/TonyCasey/lisaWrote 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/tonycasey/lisa/agents-md)<a href="https://agentmods.dev/instructions/tonycasey/lisa/agents-md"><img src="https://agentmods.dev/badge/instructions/tonycasey/lisa/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 | $0.06869 | $0.06869 |
| Opus 5 | $0.03435 | $0.03435 |
| Sonnet 5 | $0.01374 | $0.01374 |
| Haiku 4.5 | $0.00687 | $0.00687 |
Grade A, and why
lisa 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 — 749 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lisa Development Guide
Multi-CLI Architecture
Lisa supports multiple AI coding assistants through a unified, event-driven architecture:
Supported CLIs
| CLI Tool | Integration | Directory | Status |
|---|---|---|---|
| Claude Code | Lifecycle hooks | .claude/ |
Stable |
| OpenCode | Plugin system | .opencode/ |
Stable |
Shared Resources
Both CLIs share resources from .lisa/:
.lisa/ # Source of truth (shared)
├── skills/ # Memory, tasks, lisa, jira, git
├── rules/ # Coding standards
├── .env # Storage configuration
.claude/ # Claude Code specific
├── settings.json # Hook commands registered here
├── skills/
│ └── lisa/ -> ../../.lisa/skills # Subdirectory symlink
└── rules/
└── lisa/ -> ../../.lisa/rules # Subdirectory symlink
.opencode/ # OpenCode specific
├── plugin/
│ └── lisa.js # Bundled plugin
└── skills/
├── memory/ -> ../../.lisa/skills/memory
├── tasks/ -> ../../.lisa/skills/tasks
└── ... # Individual skill symlinks
Note: Lisa uses subdirectory symlinks to preserve any existing user files in .claude/ or .opencode/.
Event Mapping
Lisa events map to CLI-specific lifecycle hooks:
| Lisa Event | Claude Code | OpenCode |
|---|---|---|
session:start (startup) |
SessionStart trigger=startup |
session.created |
session:start (resume) |
SessionStart trigger=resume |
session.updated |
session:start (compact) |
SessionStart trigger=compact |
session.compacted |
session:stop (idle) |
Stop |
session.idle |
prompt:submit |
UserPromptSubmit |
message.updated |
CLI Selection
During lisa init, users can select which CLIs to support:
# Interactive (prompts for selection)
lisa init
# Non-interactive
lisa init --claude-only # Only Claude Code
lisa init --opencode-only # Only OpenCode
lisa init -y # Both (default)
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 · 749 lines · 6,869 tokens per session scan A f6afdcda920e
lisa AGENTS.md is an instructions file published in the GitHub repository TonyCasey/lisa (9 stars, last pushed 6mo ago), licensed MIT. It adds 6,869 tokens to every session, about $0.0343 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
commonplace CLAUDE.md
Instructions for itsmeduncan/commonplace, covering claude.md, what this is, deployment model (source of truth lives in two places), architecture invariants (don't break these) and config quirks that look like bugs but aren't.
infinity-context AGENTS.md
Instructions for 777genius/infinity-context, covering agents.md, project intent, source of truth and implementation rule.
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
SeekMoney-ai CLAUDE.md
Instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.