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/lando-labs/cami/claude-mdgit clone --depth 1 https://github.com/lando-labs/camiWrote 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/lando-labs/cami/claude-md)<a href="https://agentmods.dev/instructions/lando-labs/cami/claude-md"><img src="https://agentmods.dev/badge/instructions/lando-labs/cami/claude-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 5.1 | $0.08443 | $0.08443 |
| Opus 5 | $0.04222 | $0.04222 |
| Sonnet 5 | $0.01689 | $0.01689 |
| Haiku 4.5 | $0.00844 | $0.00844 |
Grade A, and why
cami CLAUDE.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 4d 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 — 1,044 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CAMI Development - Claude Agent Management Interface
CAMI Source Code Repository
This is the CAMI development repository. You are working on the Go codebase that powers CAMI's MCP server and CLI.
Claude Context: CAMI Developer Assistant
You are assisting with CAMI development - working on the Go codebase that implements the Model Context Protocol (MCP) server and CLI for Claude Code agent management.
Your Focus Areas:
-
Go Development - Write clean, idiomatic Go code following the project's patterns and conventions.
-
MCP Implementation - Understand and work with the MCP protocol implementation in
internal/mcp/. -
Agent Management Logic - Work on agent loading, deployment, source management in
internal/agent/,internal/deploy/, etc. -
Cross-Platform Support - Ensure code works on macOS, Linux, and Windows.
-
Testing & Quality - Write tests, use the QA agent for coverage, maintain code quality.
Development Workflow:
- Use
go run ./cmd/camifor local testing - The
.mcp.jsonin this repo usesgo runfor zero-setup development - Run
make buildto compile binary - Run
make testfor tests - Run
make lintfor code quality checks - Use deployed agents (qa, agent-architect) for development tasks
Remember: This is the CAMI source code repo. Users install CAMI via releases and get a clean ~/cami-workspace/ workspace with templates from install/templates/.
Architecture Overview
Single Binary, Dual Modes
# MCP Server Mode (primary) - for Claude Code
$ cami --mcp
# Runs as MCP server on stdio for Claude Code integration
# CLI Mode (secondary) - for scripting and quick checks
$ cami list
$ cami deploy frontend backend ~/projects/my-app
$ cami scan ~/projects/my-app
User Workspace Structure
CAMI creates a user workspace at ~/cami-workspace/ during installation:
~/cami-workspace/ # User workspace (created by installer)
├── CLAUDE.md # User-facing CAMI documentation
├── README.md # User quick start guide
├── .mcp.json # Local MCP config
├── .gitignore # Git ignore rules
├── config.yaml # CAMI configuration
├── .claude/
│ └── agents/ # CAMI's own agents
├── sources/ # Agent sources
│ ├── my-agents/ # User's custom agents
│ ├── team-agents/ # (if added)
│ └── fullstack-guild/ # Example: guild added via add_source
/usr/local/bin/cami # Binary (on PATH)
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.
- 4d ago First seen · 1,044 lines · 8,443 tokens per session scan A fc18a8454116
cami CLAUDE.md is an instructions file published in the GitHub repository lando-labs/cami (14 stars, last pushed 5mo ago), licensed MIT. It adds 8,443 tokens to every session, about $0.0422 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 2026-09-01.
Other instructions, from other repositories
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
unraid-management-agent copilot-instructions.md
Copilot instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
agentcat-go-sdk CLAUDE.md
Claude Code instructions for agentcathq/agentcat-go-sdk, covering claude.md, what this is, build & test commands, module layout and architecture.
oastools GEMINI.md
Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.