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 wdavidturner/product-skills --skill working-backwardsgit clone --depth 1 https://github.com/wdavidturner/product-skillsWrote 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/wdavidturner/product-skills/working-backwards)<a href="https://agentmods.dev/skills/wdavidturner/product-skills/working-backwards"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/working-backwards/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/wdavidturner/product-skills/working-backwards"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/working-backwards.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 | $0.00080 | $0.01136 |
| Opus 5 | $0.00040 | $0.00568 |
| Sonnet 5 | $0.00016 | $0.00227 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
working-backwards 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 12d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working Backwards
What It Is
Working Backwards is Amazon's product development methodology. The core insight: start with the customer problem and work backward to the solution, not the other way around.
Most teams work forward: "We have this technology/capability/idea — what can we build with it?" Working Backwards inverts this: "What problem does the customer have? What would the ideal solution look like? Now, how do we build it?"
The mechanism: Write an internal press release and FAQ before building anything. If you can't write a compelling press release, you don't have a compelling product.
As Jeff Bezos put it: "We took it as an article of faith — if we served customers well, if we prioritized customers and delivered for them, things like sales, revenue, and free cash flow would follow."
When to Use It
Use Working Backwards when you need to:
- Define a new product or major feature before committing resources
- Evaluate competing product ideas and choose which to build
- Align stakeholders on what you're building and why
- Force clarity on vague product concepts
- Prevent building solutions in search of problems
- Create a shared vision that engineering, design, and leadership can rally around
- Decide whether an idea is worth pursuing at all
When Not to Use It
- The work is incremental optimization (A/B tests, bug fixes)
- You're executing on an already-defined product
- The scope is too small to warrant the overhead
- You're just exploring technical feasibility (do that first, then write the PR/FAQ)
Patterns
Detailed examples showing how to apply Working Backwards correctly. Each pattern shows a common mistake and the correct approach.
Critical (get these wrong and you've wasted your time)
| Pattern | What It Teaches |
|---|---|
| solution-first-thinking | Don't start with the solution and retrofit a problem |
| missing-problem-paragraph | If you skip the problem, there probably isn't one |
| vague-customer-definition | "Everyone" is not a customer — be specific |
| writing-pr-after-building | The PR comes first, not as documentation after |
| internal-jargon-in-pr | Press releases are for customers, not engineers |
What ships with it
16 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.
- patterns/_template.md 460 B
- patterns/combining-ideas.md 2.1 KB
- patterns/customer-quote-sounds-fake.md 2.1 KB
- patterns/faq-avoids-hard-questions.md 2.6 KB
- patterns/faq-too-short.md 2.8 KB
- patterns/hyperbole-instead-of-specifics.md 2.2 KB
- patterns/internal-jargon-in-pr.md 2.2 KB
- patterns/missing-problem-paragraph.md 2.2 KB
- patterns/missing-the-date.md 1.7 KB
- patterns/no-measurable-outcome.md 2.1 KB
- patterns/skipping-the-iteration.md 2.4 KB
- patterns/solution-first-thinking.md 1.9 KB
- patterns/too-many-features.md 2.1 KB
- patterns/vague-customer-definition.md 1.8 KB
- patterns/writing-pr-after-building.md 2.1 KB
- references/working-backwards-playbook.md 12 KB
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.
- 12d ago First seen · 97 lines · 80 tokens per session scan A 81e1ae4fc1c7
working-backwards is a skill published in the GitHub repository wdavidturner/product-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 80 tokens to every session and 1,136 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…