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 boparaiamrit/skills-by-amrit --skill product-completeness-auditgit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/product-completeness-audit)<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/product-completeness-audit"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/product-completeness-audit/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/boparaiamrit/skills-by-amrit/product-completeness-audit"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/product-completeness-audit.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 | $0.00056 | $0.02685 |
| Opus 5 | $0.00028 | $0.01342 |
| Sonnet 5 | $0.00011 | $0.00537 |
| Haiku 4.5 | $0.00006 | $0.00268 |
Grade A, and why
product-completeness-audit 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Completeness Audit
Overview
A beautiful UI with hardcoded data is a demo, not a product. This skill systematically verifies that every page, every flow, and every component is functionally complete — not just visually complete.
Core principle: If a user cannot complete the intended journey from start to finish with real data, the product is NOT done. Period.
The Iron Law
NO PAGE IS COMPLETE UNTIL IT RENDERS REAL DATA, HANDLES ALL STATES, AND CONNECTS TO A WORKING BACKEND. VISUAL COMPLETENESS ≠ FUNCTIONAL COMPLETENESS.
When to Use
- After AI has "built" a product and you suspect placeholder pages
- When the frontend looks good but flows feel broken
- When you've integrated APIs but aren't sure everything is connected
- Before presenting a product to stakeholders
- When "it builds" but you don't trust it actually works
- After a major feature addition to verify nothing was broken
When NOT to Use
- For visual design review (use
frontend-audit) - For API design quality (use
api-design-audit) - For security concerns (use
security-audit)
The Product Completeness Spectrum
IDENTIFY where the product sits on this spectrum:
Level 0: SKELETON → Routes exist, pages are blank or show errors
Level 1: WIREFRAME → Pages render but with placeholder text/images
Level 2: DEMO → Stats/data present but hardcoded (same values on every load)
Level 3: CONNECTED → API calls exist but may fail silently or show partial data
Level 4: FUNCTIONAL → All data flows work but edge cases break
Level 5: COMPLETE → Every flow works, errors are handled, edge cases covered
MOST AI-BUILT PRODUCTS ARE AT LEVEL 1-2. YOUR JOB IS TO GET THEM TO LEVEL 5.
The Process
Phase 1: Route Inventory (MAP EVERYTHING)
1. EXTRACT every route from the application:
- Check router configuration (next.js pages/app, react-router, vue-router, etc.)
- Check for dynamic routes ([id], :id, etc.)
- Check for protected routes (auth required)
- Check for nested routes
2. CREATE the Route Inventory:
| # | Route | Page Component | Auth Required | Status |
|---|-------|---------------|---------------|--------|
| 1 | / | HomePage | No | 🔍 Not checked |
| 2 | /login | LoginPage | No | 🔍 Not checked |
| 3 | /dashboard | DashboardPage | Yes | 🔍 Not checked |
| 4 | /users/:id | UserDetailPage | Yes | 🔍 Not checked |
3. DO NOT MISS:
- 404 page
- Error pages
- Loading pages
- Auth callback pages
- Settings/profile pages
- Modal routes (if using)
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 · 328 lines · 56 tokens per session scan A 86b2f310de59
product-completeness-audit is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 2,685 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.