What is jarvis-mcp AGENTS.md?

A set of repository instructions for Jarvis, a local personal work assistant that works with Codex and other clients using MCP, a standard way for AI tools to connect to services. It describes setup, optional services, long-term Markdown memory, and desktop check-ins.

Use it when installing, configuring, repairing, or setting up Jarvis for Codex, including running its installer, initializing local memory, registering the server, and completing optional-service onboarding.

It gives Codex a defined procedure for installing and configuring Jarvis while keeping the repository author’s private settings, credentials, and memories out of the new setup.

How ash25082003/jarvis-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ash25082003/jarvis-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.

Copy the file

curl -O https://raw.githubusercontent.com/ash25082003/jarvis-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ash25082003/jarvis-mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ash25082003/jarvis-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ash25082003/jarvis-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ash25082003/jarvis-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ash25082003/jarvis-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ash25082003/jarvis-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ash25082003/jarvis-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 987 This file is loaded in full into every session.

When invoked 987 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00987	$0.00987
Opus 5.5	$0.00395	$0.00395
Sonnet 5.5	$0.00197	$0.00197
Haiku 4.5	$0.00099	$0.00099

Measured 2mo ago against content hash 79083f16917e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jarvis-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 2mo 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.

AGENTS.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jarvis MCP Repository

This repository contains Jarvis, a local-first personal work assistant for Codex and other MCP-compatible AI clients.

Set Up Jarvis For Codex

When the user asks to install, configure, repair, or set up Jarvis for Codex:

Run npm run setup:codex from the repository root.
Let the idempotent installer check prerequisites, install dependencies, build the server, initialize a new local vault, add the global Jarvis guidance to the active Codex home, register the jarvis MCP server, and install the jarvis launcher.
If the installer reports a missing prerequisite, help the user install that prerequisite and rerun the installer.
Never copy the repository author's .jarvis, .codex, .config/jarvis, credentials, memories, encryption identity, backup remote, or other personal configuration into a new installation.
Explain that core long-term Markdown memory is now active. Then continue the guided optional-service onboarding below; do not silently stop after the base installer.
After successful onboarding, tell the user to restart Codex and launch a fresh session with jarvis. Verify the MCP entry with codex mcp get jarvis if needed.

Use npm run setup:codex:check for a read-only prerequisite and path check. Detailed paths, variables, defaults, and optional-service settings are documented in docs/CONFIGURATION.md.

Guided Optional-service Onboarding

These features process private data or create background and remote resources. Explain each feature plainly and obtain the user's explicit consent before enabling it. A general request to set up Jarvis authorizes the base installer, not transcript review, notifications, or creation of a GitHub repository.

Five-hour Dream Consolidation

Explain that this feature reviews bounded windows of the user's local Codex conversations every five hours, redacts common credential formats, stores evidence-linked summaries, automatically promotes only high-confidence non-sensitive memories, and queues uncertain or sensitive candidates for review.

Read the full file on GitHub · 63 lines

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.

2mo ago First seen · 63 lines · 987 tokens per session scan A 79083f16917e

Subscribe to this mod's changes

jarvis-mcp AGENTS.md is an instructions file published in the GitHub repository ash25082003/jarvis-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 987 tokens to every session, about $0.0039 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.

jarvis-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
jarvis-mcp AGENTS.mdash25082003/jarvis-mcp	Instructions file	1	2mo ago	MIT	A	987	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

jarvis-mcp: Instructions file for Codex