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 skills add mizukaizen/hive-doctrine-mcp --skill lean-canvasgit clone --depth 1 https://github.com/mizukaizen/hive-doctrine-mcpWrote 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/skills/mizukaizen/hive-doctrine-mcp/lean-canvas)<a href="https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/lean-canvas"><img src="https://agentmods.dev/badge/skills/mizukaizen/hive-doctrine-mcp/lean-canvas/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/lean-canvas"><img src="https://agentmods.dev/badge/skills/mizukaizen/hive-doctrine-mcp/lean-canvas.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00564 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
lean-canvas 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Lean Canvas Generator
Use when starting a new product idea. Generates a structured lean canvas to force clarity on the business model before any code is written.
Trigger
Invoke this skill when the user says they have a new product idea, want to explore a business concept, or needs to articulate their value proposition.
Process
- Ask the user to describe their idea in 2-3 sentences.
- Generate a lean canvas covering all 9 blocks.
- Challenge any block that relies on assumptions without evidence.
- Save the canvas to
docs/canvases/[idea-slug]-canvas.md.
Output Template
# Lean Canvas: [Product Name]
**Date:** [YYYY-MM-DD]
**Status:** Draft / Validated / Rejected
## 1. Problem
Top 3 problems this product solves:
1. [Problem 1]
2. [Problem 2]
3. [Problem 3]
**Existing alternatives:** [How people solve this today]
## 2. Customer Segments
- **Target user:** [Who specifically]
- **Early adopters:** [Who will use v1 despite its rough edges]
## 3. Unique Value Proposition
[Single clear sentence: what makes this different and worth paying attention to]
## 4. Solution
Top 3 features that address the top 3 problems:
1. [Solution to Problem 1]
2. [Solution to Problem 2]
3. [Solution to Problem 3]
## 5. Channels
How you will reach customers:
- [Channel 1]
- [Channel 2]
## 6. Revenue Streams
- **Pricing model:** [subscription / one-time / freemium / usage-based]
- **Price point:** $[X]/[period]
- **Justification:** [Why this price]
## 7. Cost Structure
- **Fixed costs:** [hosting, domains, tools]
- **Variable costs:** [per-user costs, API calls, support]
- **Break-even:** [X] paying customers
## 8. Key Metrics
- [Metric 1 — e.g., weekly active users]
- [Metric 2 — e.g., conversion rate]
- [Metric 3 — e.g., churn rate]
## 9. Unfair Advantage
[Something that cannot be easily copied or bought — domain expertise, existing audience, proprietary data, network effects]
Rules
- If the user cannot fill "Unfair Advantage," that is fine for now — but flag it as a long-term risk.
- Challenge any revenue estimate that assumes more than 1% conversion rate without evidence.
- The canvas is a living document. Update it as validation data comes in.
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.
- 10d ago First seen · 74 lines · 0 tokens per session scan A 739d76761d8f
lean-canvas is a skill published in the GitHub repository mizukaizen/hive-doctrine-mcp (0 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 564 tokens. 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 skills, from other repositories
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
brain-in-the-fish
Universal document evaluation engine — evaluate any document against any criteria using cognitively-modelled AI agents with ontology-grounded scoring.
superagenticmcp
SuperAgenticMCP — the switchboard for your agent swarm. MCP-native router and multi-agent control plane that plans tasks, routes tool calls to racked MCP servers by capability and latency, streams execution, and files results into a memory-scope graph. Use when the user needs multi-agent orchestration over MCP, a…
go-best-practices
Go coding best practices. Use when writing or reviewing Go code. Covers error handling, concurrency, and idiomatic patterns.
typescript-best-practices
TypeScript/Node.js best practices. Use when writing or reviewing TypeScript code. Covers type safety, async patterns, and error handling.
multi-agent-governance
Use this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework.