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/bamdadd/lintel/claude-mdgit clone --depth 1 https://github.com/bamdadd/lintelWhat 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 | $0.05377 | $0.05377 |
| Opus 5 | $0.02688 | $0.02688 |
| Sonnet 5 | $0.01075 | $0.01075 |
| Haiku 4.5 | $0.00538 | $0.00538 |
Grade A, and why
lintel CLAUDE.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Make HTTP requests** to the API at `http://localhost:8000/api/v1/` using `rtk proxy curl` (bypasses token filtering for raw JSON) How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Pre-Commit Rule
Before every commit, run make lint and make typecheck and fix any errors. Do not commit code that fails linting or type checking.
Project Overview
Lintel is an open-source AI collaboration infrastructure platform. It orchestrates multi-agent workflows triggered from Slack threads, using event sourcing and CQRS patterns. Built with Python 3.12+, FastAPI, LangGraph, and PostgreSQL.
Workspace Structure
This is a uv workspace monorepo with 45+ packages under packages/:
Core packages:
| Package | Name | Dependencies | Description |
|---|---|---|---|
packages/contracts/ |
lintel-contracts |
(none) | Pure domain contracts: types, commands, events, Protocol interfaces |
packages/agents/ |
lintel-agents |
contracts | AI agent runtime (roles: planner, coder, reviewer, pm, designer, summarizer) |
packages/workflows/ |
lintel-workflows |
contracts, agents | LangGraph workflow orchestration and graph nodes |
packages/app/ |
lintel |
all below | Thin composition root: lifespan wiring, middleware, router mounting |
Reusable library packages (each independently installable):
| Package | Name | Dependencies | Description |
|---|---|---|---|
packages/event-store/ |
lintel-event-store |
contracts | Append-only event persistence (Postgres + in-memory) |
packages/event-bus/ |
lintel-event-bus |
contracts | In-memory pub/sub event bus |
packages/projections/ |
lintel-projections |
contracts, event-bus | Read-model projection engine and concrete projections |
packages/persistence/ |
lintel-persistence |
contracts | Generic CRUD/dict stores, vault |
packages/sandbox/ |
lintel-sandbox |
contracts | Docker-based code execution sandboxes |
packages/pii/ |
lintel-pii |
contracts | PII detection/anonymization (presidio) |
packages/observability/ |
lintel-observability |
contracts | OpenTelemetry tracing/metrics/logging |
packages/models/ |
lintel-models |
contracts | LLM provider routing (litellm) |
packages/slack/ |
lintel-slack |
contracts | Slack channel adapter |
packages/repos/ |
lintel-repos |
contracts | GitHub repository provider |
packages/coordination/ |
lintel-coordination |
(asyncpg only) | Database advisory locks |
packages/infrastructure/ |
lintel-infrastructure |
(residual) | MCP tool client only — will be dissolved |
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 · 321 lines · 5,377 tokens per session scan A 9d9348d6ddbc
lintel CLAUDE.md is an instructions file published in the GitHub repository bamdadd/lintel (10 stars, last pushed 4mo ago), licensed MIT. It adds 5,377 tokens to every session, about $0.0269 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
DYLA-ai AGENTS.md
Instructions for Federico-Anastasi/DYLA-ai, covering dyla — instructions for the agent, what this is, where you are running, how you work here and one skill, one deliverable.
ClauseKeeper AGENTS.md
AGENTS.md instructions for mityda/ClauseKeeper, covering agents.md — clausekeeper agent guide, open-core boundary, architecture overview, setup commands and option a: uv (preferred).
ClauseKeeper copilot-instructions.md
Copilot instructions for mityda/ClauseKeeper, covering copilot instructions for clausekeeper, how to work in this repo, architecture quick map, non-negotiable product constraints and security and privacy expectations.
ClauseKeeper clause-rules.instructions.md
Instructions for mityda/ClauseKeeper, covering clause rules and scanner instructions, rule structure, adding a jurisdiction or new legal regime safely and scanner engine expectations.
DYLA-ai CLAUDE.md
Instructions for Federico-Anastasi/DYLA-ai, covering dyla — instructions for the agent, what this is, where you are running, how you work here and one skill, one deliverable.
framework AGENTS.md
Instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.