agentmods.dev

okta_mcp AGENTS.md

A project instruction file for agents working with an Okta MCP, a connector for Okta's identity and access-management service. It defines how to start, authenticate, reconfigure, and reset the connector.

In plain words
What is it for?
Starting or configuring the Okta MCP, choosing browser or OAuth authentication, checking its setup, resetting its saved configuration, and following the project's required launch commands.
Why use it?
It gives agents a consistent setup process and prevents unsafe handling of cookies, OAuth tokens, and authentication settings.

Instructions file for CodexOpenCode

0 13d ago A scan 361 tokens original MIT
View the source file oreneHack/okta_mcp
Install

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.

agentmods
npx agentmods add instructions/orenehack/okta_mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/oreneHack/okta_mcp

Made for: Codex, OpenCode.

Per session 361 This file is loaded in full into every session.
When invoked 361 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00361 $0.00361
Opus 5 $0.00180 $0.00180
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured yesterday against content hash f781bf581e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

okta_mcp AGENTS.md 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.

AGENTS.md · 27 lines

What it actually says

Okta MCP operation

When the user asks to start, connect, configure, or authenticate the Okta MCP:

  • Call the configured okta-start MCP tool immediately.
  • Do not launch MCP Inspector. It is a development utility and is not part of the normal setup experience.
  • On first use, let okta-start ask whether to use Browser Session or OIDC/OAuth and collect only the settings required for the selected mode. Later starts reuse saved setup. Pass reconfigure=true only when the user explicitly asks to change the configuration.
  • When the user explicitly asks to reset the Okta MCP configuration, call okta-reset with confirm=true. Explain that it closes any live browser and removes this MCP's saved authentication settings and local OAuth cache. The next okta-start call presents the first-run form again.
  • If okta-start is unavailable, run npm run check:codex. If registration is missing or outdated, run npm run setup:codex, then explain that Codex must be restarted once to load the corrected absolute entrypoint. Do not use a different launcher.
  • Never request, display, or persist raw cookie values or raw OAuth tokens.
  • After Browser Session authentication, treat the isolated browser as active until okta-browser-close, MCP shutdown, manual browser close, or the idle timeout. Use okta-browser-status, okta-browser-snapshot, okta-browser-navigate, and okta-browser-read for supported read-only operations. Do not state that the temporary profile was deleted while browser_session_active is true.
Changes

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.

  1. yesterday First seen · 27 lines · 361 tokens per session scan A f781bf581e88

Subscribe to this mod's changes

okta_mcp AGENTS.md is an instructions file published in the GitHub repository oreneHack/okta_mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 361 tokens to every session, about $0.0018 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 2026-08-31.

Browser automationSecurity
Related

Other instructions, from other repositories

Browser4 CLAUDE.md

Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

deepseekCLI CLAUDE.md

Instructions for cynchro/deepseekCLI, covering tarea actual, progreso, decisiones clave, próximos pasos and contexto importante.

cynchro/deepseekCLI · 1,728 tokens

deckforge AGENTS.md

Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.

tph-kds/deckforge · 498 tokens

fast-browser CLAUDE.md

Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.

m4ttstack/fast-browser · 1,446 tokens

agentoscope AGENTS.md

Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.

rafaelcg/agentoscope · 664 tokens

sendblue-browser-use AGENTS.md

Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).

sendblue-api/sendblue-browser-use · 1,064 tokens