lisa CLAUDE.md

lisa CLAUDE.md is an instructions file for coding agents from TonyCasey/lisa. It costs 2,050 tokens per session, scanned B, original, MIT.

A long-term memory and task-tracking system for Claude Code, the coding assistant. It preserves useful context between coding sessions and stores project guidance, tasks, and related information.

In plain words
What is it for?
Use it to build the project, run tests or linting, restore past session context, track tasks, and retain project knowledge.
Why use it?
It reduces the need to repeatedly explain project decisions and unfinished work after context is lost or a new session begins.

Instructions file

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/tonycasey/lisa/claude-md
Clone the repo
git clone --depth 1 https://github.com/TonyCasey/lisa

Wrote 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.

agentmods badge for lisa CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tonycasey/lisa/claude-md.svg)](https://agentmods.dev/instructions/tonycasey/lisa/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tonycasey/lisa/claude-md"><img src="https://agentmods.dev/badge/instructions/tonycasey/lisa/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,050 This file is loaded in full into every session.
When invoked 2,050 The same file — it is already loaded in full.
Security scan B 1 finding. 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 5.1 $0.02050 $0.02050
Opus 5 $0.01025 $0.01025
Sonnet 5 $0.00410 $0.00410
Haiku 4.5 $0.00205 $0.00205

Measured 5d ago against content hash fb8f84be6060, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

lisa CLAUDE.md scanned grade B with 1 finding 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep "yourFunction" .claude/hooks/session-start.js
CLAUDE.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lisa - Claude Code Memory System

Long-term memory for Claude Code. Automatic context persistence, task tracking, and knowledge capture across coding sessions.

Quick Reference

Command Description
npm run build Compile TypeScript and deploy to .claude/, .lisa/
npm test Run all unit tests
npm run lint Run ESLint

Project Structure

lisa/
├── src/
│   ├── lib/                      # Core library code
│   │   ├── cli.ts                # Main CLI entry point
│   │   ├── services.ts           # Service factory
│   │   ├── domain/               # Domain types and contracts
│   │   ├── infrastructure/       # DAL, adapters
│   │   └── application/          # Use cases
│   └── project/                  # Templates (mirrors deployment)
│       ├── .lisa/
│       │   ├── skills/           # Memory, tasks, lisa, jira, git
│       │   │   ├── common/       # Shared group-id, type maps
│       │   │   └── shared/utils/ # DI-based utilities
│       │   ├── rules/            # Coding standards
│       │   └── docker/           # docker-compose.graphiti.yml
│       ├── .claude/
│       │   ├── hooks/            # session-start, session-stop, etc.
│       │   │   └── utils/        # Hook utilities (common, core, io, session)
│       │   └── config.ts
│       └── .opencode/
│           └── plugin/           # OpenCode plugin source
├── .claude/                      # Deployed hooks (compiled output)
│   ├── hooks/                    # Compiled JS hooks
│   ├── skills -> ../.lisa/skills
│   └── rules -> ../.lisa/rules
├── .lisa/                        # Deployed skills and rules (shared)
│   ├── skills/
│   ├── rules/
│   └── docker/
├── .opencode/                    # Deployed OpenCode plugin
│   ├── plugin/
│   └── skill -> ../.lisa/skills
├── tests/
│   └── unit/                     # Unit tests (mirror src/ structure)
└── dist/                         # Compiled library output

Development Workflow: "Reverse Engineering"

Read the full file on GitHub · 268 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. 5d ago First seen · 268 lines · 2,050 tokens per session scan B fb8f84be6060

Subscribe to this mod's changes

lisa CLAUDE.md is an instructions file published in the GitHub repository TonyCasey/lisa (9 stars, last pushed 6mo ago), licensed MIT. It adds 2,050 tokens to every session, about $0.0103 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.