Borrowing it
Nothing to install: this file belongs to oreneHack/okta_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oreneHack/okta_mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/oreneHack/okta_mcpWrote 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/instructions/orenehack/okta_mcp/agents-md)<a href="https://agentmods.dev/instructions/orenehack/okta_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/orenehack/okta_mcp/agents-md/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/instructions/orenehack/okta_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/orenehack/okta_mcp/agents-md.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 | $0.00361 | $0.00361 |
| Opus 5.5 | $0.00144 | $0.00144 |
| Sonnet 5.5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
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 1mo 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.
What it actually says
Okta MCP operation
When the user asks to start, connect, configure, or authenticate the Okta MCP:
- Call the configured
okta-startMCP 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-startask whether to use Browser Session or OIDC/OAuth and collect only the settings required for the selected mode. Later starts reuse saved setup. Passreconfigure=trueonly when the user explicitly asks to change the configuration. - When the user explicitly asks to reset the Okta MCP configuration, call
okta-resetwithconfirm=true. Explain that it closes any live browser and removes this MCP's saved authentication settings and local OAuth cache. The nextokta-startcall presents the first-run form again. - If
okta-startis unavailable, runnpm run check:codex. If registration is missing or outdated, runnpm 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. Useokta-browser-status,okta-browser-snapshot,okta-browser-navigate, andokta-browser-readfor supported read-only operations. Do not state that the temporary profile was deleted whilebrowser_session_activeis true.
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.
- 1mo ago First seen · 27 lines · 361 tokens per session scan A f781bf581e88
okta_mcp AGENTS.md is an instructions file published in the GitHub repository oreneHack/okta_mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 361 tokens to every session, about $0.0014 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.