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 hardiktiwari/PM-operating-OS --skill working-backwardsgit clone --depth 1 https://github.com/hardiktiwari/PM-operating-OSWrote 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/hardiktiwari/pm-operating-os/working-backwards)<a href="https://agentmods.dev/skills/hardiktiwari/pm-operating-os/working-backwards"><img src="https://agentmods.dev/badge/skills/hardiktiwari/pm-operating-os/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/hardiktiwari/pm-operating-os/working-backwards"><img src="https://agentmods.dev/badge/skills/hardiktiwari/pm-operating-os/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 | $0.00033 | $0.00580 |
| Opus 5 | $0.00016 | $0.00290 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working Backwards
Help PMs apply the working backwards methodology: start from the customer and desired outcome, then work backward to define the product. Produces PR/FAQ, press release, and customer-first plans.
When to Use
- Defining a new product or major initiative
- Writing a PR/FAQ (Press Release / Frequently Asked Questions)
- Planning from a future state
- Clarifying value proposition before building
- When asked "help me think backwards" or "write a press release"
Process / Template
1. Define the Future State
- Customer — who is this for?
- Problem — what pain are we solving?
- Ideal outcome — what does success look like for the customer?
- Emotional payoff — how does the customer feel when it works?
2. Write the Press Release
Imagine the product is launched. Write a 1-page press release as if it's real:
Headline
- Bold, benefit-focused (not feature-focused)
Subhead
- One sentence: who it's for and why it matters
Problem
- 1–2 paragraphs: the pain today
Solution
- What we built and how it solves the problem
Quote
- Customer or executive quote (aspirational)
Call to Action
- How to get it, try it, learn more
Closing
- Company boilerplate (optional)
3. Write the FAQ
Anticipate questions from internal and external audiences:
Customer FAQ
- What is it? How do I get it? How much does it cost?
- What if I have [edge case]?
Internal FAQ
- Why are we building this? What's the business model?
- What are we not building? What's out of scope?
- How will we measure success? What could go wrong?
4. Derive Requirements
From the press release and FAQ:
- What must be true for the press release to be accurate?
- What are the must-have capabilities?
- What can we defer to v2?
5. Validate
- Does the press release pass the "so what?" test?
- Would a customer care? Would they share it?
- Is the problem real and meaningful?
Output
A Working Backwards Package including:
- Press Release — 1 page, customer-facing, benefit-led
- FAQ — customer and internal questions with answers
- Implications — what we must build (high-level)
What ships with it
1 file 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.
- 9d ago First seen · 86 lines · 33 tokens per session scan A bac160cfdb35
working-backwards is a skill published in the GitHub repository hardiktiwari/PM-operating-OS (5 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 580 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 2026-08-31.
Other skills, from other repositories
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…
sdd
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
bcc-throughline
BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.