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 commands/phazurlabs/install-labs/agent-guidegit clone --depth 1 https://github.com/phazurlabs/install-labsWhat 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 | $0.00022 | $0.02450 |
| Opus 5 | $0.00011 | $0.01225 |
| Sonnet 5 | $0.00004 | $0.00490 |
| Haiku 4.5 | $0.00002 | $0.00245 |
Grade A, and why
agent-guide 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agent-guide — Orientation & Routing
Purpose
The entry point for turning any AI agent or automation into an installable package. Assess what the user built, show them the full journey, and route them to the right next step.
Protocol
When the user invokes /agent-guide, follow this process exactly:
Step 1: Assess What the User Built
Determine the agent's type, framework, target audience, and infrastructure requirements. Ask the user directly or infer from context they have already provided.
Gather these five dimensions:
| Dimension | Question | Examples |
|---|---|---|
| Framework / Platform | What did you build it with? | LangChain, CrewAI, AutoGen, LangGraph, DSPy, Haystack, custom Python, custom Node.js/TypeScript, n8n, Flowise, Dify, ComfyUI, Make/Zapier, browser automation (Playwright/Puppeteer), shell scripts |
| Agent Behavior | What does the agent do? | Conversational assistant, tool-using agent, multi-agent system, workflow automation, RAG pipeline, image/video generation, data extraction, code generation, research agent, monitoring/alerting |
| Target Audience | Who will install and use it? | Developers comfortable with CLI, non-technical business users, enterprise IT teams, other AI agents (agent-to-agent), open source community |
| Runtime Model | How should it run? | Locally on the user's machine, cloud-hosted (SaaS), hybrid (local agent + cloud APIs), edge device, ephemeral (runs once and exits) |
| Dependencies | What does it need to function? | API keys only, local model weights (specify size), database (Postgres, SQLite), vector store (ChromaDB, Pinecone, Qdrant), GPU (CUDA/Metal), system tools (ffmpeg, Chrome, etc.) |
Inference rules:
- If the user says "I built a CrewAI agent that researches companies," infer: Framework = CrewAI (Python), Behavior = research agent (tool-using, multi-agent), Dependencies = likely API keys + possibly a search API. Ask only what you cannot infer.
- If the user points to a GitHub repo or local directory, scan the codebase to identify the framework (look for
requirements.txt,package.json,pyproject.toml,Dockerfile,crew.yaml,langgraph.json,n8nworkflow exports, etc.). - If the user says "I have an MCP server," they may already know their distribution target. Confirm and skip to
/pick-targetor/gen-package.
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 · 181 lines · 22 tokens per session scan A 81d80a3d2ee5
agent-guide is a command published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 2,450 once invoked, about $0.0001 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 commands, from other repositories
build
Run full verification pipeline.
quality
Review code for quality improvements.
refactor
Suggest refactoring opportunities.
security-review
Review code for security vulnerabilities.
test-coverage
Analyze test coverage and suggest improvements.
test-e2e
Write end-to-end tests for critical user journeys.