Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rafaelszago/doc-everythingnpx agentmods add rules/rafaelszago/doc-everything/document-feature-productWrote 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/rules/rafaelszago/doc-everything/document-feature-product)<a href="https://agentmods.dev/rules/rafaelszago/doc-everything/document-feature-product"><img src="https://agentmods.dev/badge/rules/rafaelszago/doc-everything/document-feature-product/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/rules/rafaelszago/doc-everything/document-feature-product"><img src="https://agentmods.dev/badge/rules/rafaelszago/doc-everything/document-feature-product.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 | $0.00089 | $0.00871 |
| Opus 5.5 | $0.00036 | $0.00348 |
| Sonnet 5.5 | $0.00018 | $0.00174 |
| Haiku 4.5 | $0.00009 | $0.00087 |
Grade A, and why
document-feature-product 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document a feature — product
Record the user-facing view of a feature: what it does, who it's for, and
how a person moves through it. Companion to the document-feature-technical
rule (the engineering view). Describe the experience and the value to the user,
not the implementation.
Where it goes
docs/features/<feature>/product.md ← this rule
docs/features/README.md ← index — this rule owns it
docs/features/<feature>/technical.md ← document-feature-technical rule
<feature>is a kebab-case slug — the same slug used by the matchingtechnical.md.- If this project pins the docs directory elsewhere (via
.cursor/doc-everything.jsonor.claude/doc-everything.jsondocsPath, or theDOC_EVERYTHING_DOCS_PATHenv var), use that path instead ofdocs/features/. - One file per feature — update
product.mdin place as behavior changes.
How to write it
- Describe what ships, not the roadmap. If a feature is scaffolded/stubbed, say so plainly in the journey.
- Fill the template. Skip a section in one line if it doesn't apply.
- Always update
docs/features/README.md— add/refresh the one-line entry for this feature so the index stays a complete map of the product. - Cross-link the matching
technical.md. - If the product has copy/localization or a visual/design language worth noting (tone, terminology, colors that carry meaning), capture it — see the optional sections in the template.
Template
# <Feature> — product
> Technical view: ./technical.md
## What it is
One line: the feature in user terms, and who it's for.
## Why it exists
The problem it solves and the value it delivers.
## Where the user finds it
Entry points the user actually reaches (route/screen, nav item, trigger).
## User journey
Numbered steps of what the user sees and does, start to finish. Quote key UI
copy where it matters.
## States & edge cases
Loading, empty, error, success — and any gating (signed-out, incomplete setup,
plan-locked). What the user sees in each.
## Copy & localization
(Optional) Primary language and any translations; where the copy lives. Note if
copy is centralized (content files) vs hardcoded.
## Visual language
(Optional) Design tokens / accent meaning / iconography this feature relies on,
and any conventions it must respect.
## Out of scope / future
What this feature deliberately does not do yet.
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.
- 1mo ago First seen · 98 lines · 89 tokens per session scan A 7d8e171139c4
document-feature-product is a cursor rule published in the GitHub repository rafaelszago/doc-everything (2 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 871 once invoked, about $0.0004 per session on Opus 5.5. 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).