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/317-okta)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/317-okta"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/317-okta.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 | $0.00039 | $0.05209 |
| Opus 5 | $0.00019 | $0.02604 |
| Sonnet 5 | $0.00008 | $0.01042 |
| Haiku 4.5 | $0.00004 | $0.00521 |
Grade D, and why
317-okta scanned grade D with 2 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 7d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **MFA on elevation** (sudo / admin commands) Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- **No shared bastion credentials**; no `~/.ssh/authorized_keys` drift How it starts
The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Okta Workforce Identity
Audience: engineers designing, operating, or auditing Okta Workforce Identity (SSO, MFA, lifecycle, Workflows, Advanced Server Access).
Scope: Okta Workforce Identity Cloud (WIC). For Customer Identity Cloud (formerly Auth0), see Auth0 documentation - patterns overlap but are not identical.
[!IMPORTANT] This rule complements:
315-iam.mdc- protocol reference (OIDC/SAML/PKCE/PKI)316-zero-trust.mdc- Zero Trust principles (always-on)180-terraform.mdc- Terraform patterns (forterraform-provider-okta)Use this rule for Okta-specific decisions: app config, policies, SCIM, Workflows, API usage, and Terraform modelling.
Non-negotiables
- MFA required for all users (WebAuthn / FIDO2 preferred; TOTP acceptable; SMS is legacy)
- Phishing-resistant MFA for privileged roles (Super Admin, Org Admin, App Admin on sensitive apps)
- No long-lived API tokens in code or config - use OAuth 2.0 for Okta or scoped, rotated SSWS tokens in a vault
- All apps use OIDC or SAML with signed responses, audience and issuer validation, and short assertion lifetimes
- Source of truth for identities is the HRIS (Workday, BambooHR, etc.) or IdP-to-IdP federation, not manual Okta user creation
- Audit log exported to SIEM (System Log API or Event Hooks), retention aligned with policy
- Terraform-managed org (
terraform-provider-okta) for any non-trivial config; no click-ops drift
Org and Environment Model
Orgs (tenants)
- Production org - real users, real apps
- Preview/sandbox org - test config changes, Workflows, API automations
- Optional per-env orgs for isolation of dev/stage/prod app configurations
Realms (if using Identity Engine Realms)
- Use realms to segment user populations (employees, contractors, partners) with distinct policies
- Do not use realms as a substitute for separate orgs when compliance requires full isolation
Admin access
- No standing Super Admin access for humans - use just-in-time elevation with approval
- Scoped admin roles (Group Admin, App Admin for specific apps) preferred over broad roles
- Service principals for automation use scoped admin roles, not Super Admin
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.
- 7d ago First seen · 498 lines · 39 tokens per session scan D c4bfa1aab84c
317-okta is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 5,209 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). 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.
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.