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/315-iamgit 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/315-iam)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/315-iam"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/315-iam.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 | $0.00034 | $0.03439 |
| Opus 5 | $0.00017 | $0.01720 |
| Sonnet 5 | $0.00007 | $0.00688 |
| Haiku 4.5 | $0.00003 | $0.00344 |
Grade A, and why
315-iam 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 6d 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity, Access, and Authentication (IAM, OIDC, SAML, PKCE, PKI, PAM)
Audience: engineers designing authentication/authorization and cloud access patterns Goal: build secure-by-default identity systems with least privilege, strong verification, and clean operations
[!IMPORTANT] This ruleset complements
310-security.mdc(OWASP) and320-api-design.mdc(API auth patterns). Use this for identity-specific decisions: token validation, federation, access boundaries, and certificate lifecycle.
Non-negotiables
- Default deny: no implicit access - access must be explicitly granted
- Least privilege: minimal actions, minimal resources, minimal time (short-lived creds)
- Separation of duties: admin != deploy != runtime
- No secret material in logs: never log passwords, tokens, session cookies, private keys, assertions
- Prove authenticity: always validate signatures (JWT/JWS, SAML XML signature), issuer, audience, and time bounds
- Assume breach: monitor, rotate, revoke, and limit blast radius
Security research and citation discipline
- Prefer current primary sources: standards bodies, protocol specifications, and official vendor documentation.
- Cite a standard by name. Include an RFC, NIST publication, or CVE identifier only after verifying it.
- Never invent a plausible-looking specification, control, CVE, feature, or version number.
- State uncertainty plainly and identify what must be verified before implementation.
- Recheck current vendor documentation when behavior depends on defaults, supported flows, versions, or recently disclosed vulnerabilities.
For OAuth deployments, use the current Best Current Practice for OAuth 2.0 Security (RFC 9700 / BCP 240) alongside the applicable base and extension specifications.
IAM (cloud access control)
Policy design principles
- Prefer roles over users for workloads and automation
- Prefer short-lived credentials (STS, workload identity) over long-lived access keys
- Use conditions to reduce blast radius:
- source IP / VPC conditions (when valid)
- required tags (ABAC)
- MFA requirement for interactive access
- session duration limits
- Use boundaries and guardrails:
- permission boundaries for roles created by automation
- org-level controls (SCPs) where applicable
- break-glass roles with strong protections and monitoring
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.
- 6d ago First seen · 374 lines · 34 tokens per session scan A 9b8f0f5821fb
315-iam is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 3,439 once invoked, about $0.0002 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
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.