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 agentmods add rules/d-padmanabhan/agent-engineering-handbook/010-workflowgit 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/010-workflow)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/010-workflow"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/010-workflow.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 | $0.00781 | $0.00781 |
| Opus 5 | $0.00391 | $0.00391 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
010-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Workflow Gates
Stable Handbook Root
Resolve the handbook root from the current user's home directory:
HANDBOOK_ROOT="${HOME}/.cursor/agent-engineering-handbook"
Agents operating in any workspace MUST resolve handbook rules, skills, commands, references, hooks, and templates from this root, not from the active repository. Handbook-internal references use literal ${HANDBOOK_ROOT}/... paths. Do not expand them into a user-specific absolute path in authored content.
Classify Before Acting
- Answer, explain, diagnose, review, or status requests are read-only unless the user also requests a change.
- A trivial, obvious, low-risk local edit may proceed directly with proportionate verification.
- Non-trivial work requires a brief plan and explicit user approval before implementation.
- Complex, architectural, security-sensitive, destructive, or broad work requires a documented plan with scope, non-goals, risks, affected areas, and verification.
- A remote mutation requires authorization under the agent audit rule (
${HANDBOOK_ROOT}/rules/020-agent-audit.mdc), regardless of task size.
Plan Gate
Before non-trivial implementation:
- Inspect the smallest relevant code and current repository state.
- State the intended outcome, scope, assumptions, risks, and verification.
- Resolve only choices that materially change the implementation.
- Wait for explicit approval.
Do not demand a formal plan for typos, narrowly scoped obvious fixes, or read-only analysis.
Implementation Gate
- Implement only the approved scope and preserve unrelated user work.
- Prefer the smallest coherent change; do not add speculative features or broad cleanup.
- Validate dependencies and configuration before relying on them.
- Stop and re-plan when implementation reveals a material architectural, destructive, security, or scope change.
- Update durable context only when the task is long-running or must survive a context reset.
Review Gate
- Verify the result in proportion to risk using available tests, lint, format, type checks, builds, or focused substitutes.
- Compare the result to the approved scope and inspect the final diff.
- Report what changed, verification performed, known limitations, and any deferred issue.
- Do not implement review follow-ups unless they are within the approved scope.
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.
- 5d ago First seen · 70 lines · 781 tokens per session scan A eacd619e413f
010-workflow is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 5d ago), licensed MIT. It adds 781 tokens to every session, about $0.0039 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.
Other cursor rules, from other repositories
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.
family-instance-domain-actions
Family instance domain action implementation patterns.
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.