working-backwards

working-backwards is a skill for Claude Code, Codex from theagenticguy/erpaval. It costs 134 tokens per session (1,791 once invoked), scanned A, original, MIT.

A five-stage product-discovery process that starts with customer questions and ends with a tested product definition. It can produce a 5CQ, a PR/FAQ, or a letter written to customers.

In plain words
What is it for?
Use it to work backwards from customer needs, define a product, draft a PR/FAQ, or prepare customer-focused product questions.
Why use it?
It helps turn uncertain product ideas into a clearer problem, proposed solution, and set of questions to test.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the erpaval plugin — 11 skills, 1 agent, 3 hooks, 5 MCP servers shipped together

Install

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.

agentmods
npx agentmods add skills/theagenticguy/erpaval/working-backwards
Any agent
npx skills add theagenticguy/erpaval --skill working-backwards
Clone the repo
git clone --depth 1 https://github.com/theagenticguy/erpaval

Made for: Claude Code, Codex.

Or install erpaval, the plugin that ships this one along with the rest of its 11 skills, 1 agent, 3 hooks, 5 MCP servers.

Wrote 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.

agentmods badge for working-backwards

README.md
[![agentmods](https://agentmods.dev/badge/skills/theagenticguy/erpaval/working-backwards.svg)](https://agentmods.dev/skills/theagenticguy/erpaval/working-backwards)
Your own site
<a href="https://agentmods.dev/skills/theagenticguy/erpaval/working-backwards"><img src="https://agentmods.dev/badge/skills/theagenticguy/erpaval/working-backwards.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,791 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00134 $0.01791
Opus 5 $0.00067 $0.00896
Sonnet 5 $0.00027 $0.00358
Haiku 4.5 $0.00013 $0.00179

Measured 4d ago against content hash c0e274d84992, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

skills/working-backwards/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contents

File Path When to load
Canonical WB reference ${CLAUDE_PLUGIN_ROOT}/skills/product-design-shared/references/working-backwards.md 5-stage process, artifacts, principles, common pitfalls
Pyramid composition ${CLAUDE_PLUGIN_ROOT}/skills/product-design-shared/references/pyramid-principle.md PR as Pyramid top, FAQ as antagonist test
Research design ${CLAUDE_PLUGIN_ROOT}/skills/product-design-shared/references/research-design.md Listen-stage hypothesis + MECE sub-questions
PR/FAQ authoring workflow references/prfaq-authoring.md Drafting workflow: 5CQ → PR → FAQ → visuals
Customer-insights role references/roles/customer-insights.md Researcher-agent role for Listen synthesis
5CQ worksheet templates/5cq-worksheet.md Fill-in-the-blank for the 5 Customer Questions

Working Backwards

Orchestrate the 5-stage Working Backwards process end-to-end to produce a 5CQ, PR/FAQ, or Dear Customer Letter. This skill is the user-facing runner; the canonical discipline lives in the shared reference at ${CLAUDE_PLUGIN_ROOT}/skills/product-design-shared/references/working-backwards.md.

When to Use

  • You have a product idea and need to pressure-test it customer-first before building.
  • You need to produce a PR/FAQ for an annual planning cycle or leadership review.
  • You need a 5CQ to align a small team on a feature idea without the full PR/FAQ overhead.
  • The real customer problem is fuzzy and you want the discipline to force clarity.

Read the full file on GitHub · 111 lines

Files

What ships with it

3 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.

Changes

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.

  1. 4d ago First seen · 111 lines · 134 tokens per session scan A c0e274d84992

Subscribe to this mod's changes

working-backwards is a skill published in the GitHub repository theagenticguy/erpaval (27 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 1,791 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

review

Use when DISCOVER or REFRESH has surfaced a proposal staged at -context.proposed/, to inspect it and record sign-off before applying it.

nick-railsback/skill-engine · 33 tokens

status

Use when picking up a contextualizer after a gap, or checking reference freshness and pending review work at a glance — read-only, safe to run anytime.

nick-railsback/skill-engine · 33 tokens

discover

Use when a contextualizer's reference coverage needs to grow against its registered sources — a fresh contextualizer's first pass, quarterly upkeep, or whenever the catalog is lagging what users are asking — to propose new reference files.

nick-railsback/skill-engine · 47 tokens

new-reference

Use when a single topic is already identified and a full DISCOVER pass would be overkill, to register one new reference in an existing contextualizer.

nick-railsback/skill-engine · 33 tokens

refresh

Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.

nick-railsback/skill-engine · 40 tokens

using-skill-engine

When the user mentions skill-engine or "the engine" without naming a specific workflow, or wants first-run setup. Inspects .claude/skills/-context/ install state (and any pending -context.proposed/ proposals) across all three install levels, then dispatches to engine-bootstrap when no contextualizer exists, to…

nick-railsback/skill-engine · 101 tokens