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.
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/800-markdown)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/800-markdown"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/800-markdown.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00696 |
| Opus 5 | $0.00000 | $0.00348 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
800-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Documentation Gates
This rule owns mandatory Markdown policy only. Use the documentation standards skill (${HANDBOOK_ROOT}/skills/documentation-standards/SKILL.md) for document design, generated PNG diagrams, templates, ADRs, and writing workflows.
Structure and Proportionality
- Start standalone documents with one clear H1 and use a logical heading hierarchy without skipped levels.
- Add a table of contents, conclusion, alert, or diagram only when the document's complexity benefits from it. Do not force ceremony onto a short note or changelog entry.
- Use lists for sequences or sets and tables only when comparison across aligned columns is materially clearer.
- Avoid decorative emojis in professional technical documentation.
Prose and Code
- Keep each prose paragraph on one source line and let the renderer soft-wrap it. Do not hard-wrap prose at a fixed column.
- Break lists, tables, front matter, code, and diagrams only as their syntax requires.
- Use fenced code blocks with the correct language identifier and complete, safe examples.
- Do not use comments, headings, or callouts as decoration or to repeat nearby prose.
- Never author Unicode em dash (
U+2014) or en dash (U+2013) characters. Use commas, colons, parentheses, semicolons, or ASCII hyphens instead. Preserve opaque external data only when exact bytes matter.
Links and Navigation
- Navigational URLs and repository paths must be clickable Markdown links with descriptive text; do not wrap links intended for navigation in backticks.
- Ordinary project documentation uses portable repository-relative links for same-repository navigation.
- Handbook-internal cross-file links use
${HANDBOOK_ROOT}/...so agents working in another repository resolve the correct source. - Literal URL or path values shown as configuration, syntax, logs, or examples may use inline code.
- Verify changed links and anchors.
Alerts and Diagrams
- Use only supported GitHub alerts:
NOTE,TIP,IMPORTANT,WARNING, andCAUTION. - Keep alerts concise and place them next to the relevant instruction.
- Do not author Mermaid diagrams in Markdown or MDX.
- Add a diagram only when a relationship, sequence, state, hierarchy, or timeline is clearer visually than in short prose.
- Create an
images/directory beside the Markdown file, generate the diagram as a descriptively named PNG inside that directory, and embed it with meaningful alt text through a portable relative path such asimages/request-flow.png. - Do not create an
images/directory when the document does not need an image. - Keep diagrams focused and readable at the rendered size. Exclude secrets, sensitive data, internal credentials, and unnecessary production identifiers.
- Verify that every referenced image exists, renders correctly, and matches the surrounding explanation before completion.
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.
- today Changed · +4 lines 3d65a24315da
- 4d ago First seen · 51 lines · 0 tokens per session scan A 90312217936a
800-markdown is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 696 tokens. 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 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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.