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 getcrew44/crew44 --skill recommendation-canvasgit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/getcrew44/crew44/recommendation-canvas)<a href="https://agentmods.dev/skills/getcrew44/crew44/recommendation-canvas"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/recommendation-canvas.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 | $0.00032 | $0.03173 |
| Opus 5 | $0.00016 | $0.01587 |
| Sonnet 5 | $0.00006 | $0.00635 |
| Haiku 4.5 | $0.00003 | $0.00317 |
Grade A, and why
recommendation-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 7d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Evaluate and propose AI product solutions using a structured canvas that assesses business outcomes, customer outcomes, problem framing, solution hypotheses, positioning, risks, and value justification. Use this to build a comprehensive, defensible recommendation for stakeholders and decision-makers—especially when proposing AI-powered features or products that carry higher uncertainty and risk.
This is not a feature spec—it's a strategic proposal that articulates why this AI solution is worth building, what assumptions need validating, and how you'll measure success.
Key Concepts
The Recommendation Canvas Framework
Created for Dean Peters' Productside "AI Innovation for Product Managers" class, the canvas synthesizes multiple PM frameworks into one strategic view:
Core Components:
- Business Outcome: What's in it for the business?
- Product Outcome: What's in it for the customer?
- Problem Statement: Persona-centric problem framing
- Solution Hypothesis: If/then hypothesis with experiments
- Positioning Statement: Value prop and differentiation
- Assumptions & Unknowns: What could invalidate this?
- PESTEL Risks: Political, Economic, Social, Technological, Environmental, Legal
- Value Justification: Why this is worth doing
- Success Metrics: SMART metrics to measure impact
- What's Next: Strategic next steps
Why This Works
- Outcome-driven: Forces clarity on business AND customer value
- Hypothesis-centric: Treats solution as a bet to validate, not a commitment
- Risk-explicit: Makes assumptions and risks visible upfront
- Executive-friendly: Comprehensive but structured for C-level review
- AI-appropriate: Especially useful for AI features with high uncertainty
Anti-Patterns (What This Is NOT)
- Not a PRD: This is strategic framing, not detailed requirements
- Not a business case (yet): It informs the business case but needs validation first
- Not a feature list: Focus on outcomes, not capabilities
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 376 lines · 32 tokens per session scan A 107be6b9306a
recommendation-canvas is a skill published in the GitHub repository getcrew44/crew44 (359 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 3,173 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
mine-plan-create
Create or update an evidence-backed, architecture-governed software implementation plan that is precise enough for independent coding agents to execute without rediscovering design decisions. Scope-first: an explicit user scope defines the planning boundary; research-backed: substantive planning requires mandatory…