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/810-documentation)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/810-documentation"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/810-documentation/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/d-padmanabhan/agent-engineering-handbook/810-documentation"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/810-documentation.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 | $0.00000 | $0.00858 |
| Opus 5 | $0.00000 | $0.00429 |
| Sonnet 5 | $0.00000 | $0.00172 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
810-documentation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Engineering Gates
This rule owns mandatory documentation policy only. Use the documentation standards skill (${HANDBOOK_ROOT}/skills/documentation-standards/SKILL.md) for workflows, templates, Docusaurus, ADRs, and technical-writing guidance. Use the Markdown rule (${HANDBOOK_ROOT}/rules/800-markdown.mdc) for Markdown structure, links, alerts, generated PNG diagrams, and accessibility. Use the utilities rule (${HANDBOOK_ROOT}/rules/120-utilities.mdc) for external documentation research and tool selection.
Purpose and Structure
- Identify the audience, task, prerequisite knowledge, and desired outcome before writing.
- Give each page one primary Diataxis mode: tutorial, how-to guide, reference, or explanation. Split pages that mix incompatible purposes without a clear reason.
- Keep navigation and information architecture proportional to the documentation set. Do not add a documentation site, versioning system, search service, or generated portal when a README and a few guides are sufficient.
- Keep documentation close to its source of truth and assign ownership for content that must remain operationally current.
Correctness and Currency
- Ground technical claims in current code, configuration, command output, schemas, or authoritative documentation.
- Verify current vendor terminology, service names, versions, defaults, limits, and compatibility before publishing them. Do not present estimates or unsupported percentages as measured facts.
- Make examples complete, safe, and runnable as shown. Pin tools and dependencies where reproducibility matters, and update the lockfile when dependencies change.
- Document prerequisites, failure behavior, validation steps, rollback or recovery when relevant, and the supported version or environment boundary.
- Remove stale examples and contradictory guidance instead of preserving them for completeness.
Security and Trust Boundaries
- Treat MDX as executable code. Do not compile untrusted JSX, imports, exports, raw HTML, or plugins in a privileged documentation build.
- Keep credentials, private incident data, customer data, internal identifiers, and sensitive production configuration out of examples, screenshots, generated images, logs, and build artifacts.
- Use synthetic
acme.comexamples and clearly distinguish placeholders from values that can be copied safely. - Give documentation builds least privilege, bounded network access, immutable dependency installation, and no production mutation authority unless the workflow explicitly requires and protects it.
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.
- yesterday Changed · -567 lines · -13 tokens per session 497f6fa7929a
- 5d ago First seen · 630 lines · 13 tokens per session scan A 8cb4e7694517
810-documentation is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 858 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.