What is hara-mcp AGENTS.md?

Repository-specific instructions for hara-mcp, an MCP gateway that connects clients to Hara execution hosts. They define the project’s responsibilities, security boundaries, development workflow, and required checks.

Use them when modifying hara-mcp to understand its scope, preserve its security rules, follow its change process, and validate required behaviour.

They help coding agents avoid changing parts of the system owned elsewhere or weakening protections around browsers, networks, credentials, relays, and message delivery.

How hara-lang/hara-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hara-lang/hara-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/hara-lang/hara-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hara-lang/hara-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/hara-lang/hara-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/hara-lang/hara-mcp/agents-md)

Your own site

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

Per session 550 This file is loaded in full into every session.

When invoked 550 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	$0.00550	$0.00550
Opus 5.5	$0.00220	$0.00220
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 71d97d554ca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hara-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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions

Scope

This repository owns the MCP gateway, host registry, routing, temporary source/result projection, and protocol adapters for Hara execution hosts. It does not own Hara evaluation semantics, Chrome/browser capabilities, Greenways application records, or a second Sandbox/LiveSession implementation.

Required boundaries

Keep the public pure catalogue limited to hara_runtime_get, hara_eval, hara_call, and hara_check until its owning issue changes.
A pure tool must never enable browser, network, persistent filesystem, package, process, database, shell, provider, or external-effect authority through options.
Never pass MCP bearer credentials to an execution host or device credentials to an MCP client.
Keep the Phase 1 relay bound exactly to 127.0.0.1. Do not add wildcard, LAN, public, or implicit bind modes.
Treat the loopback bearer token as transport-only authority. Never place it in descriptors, Hara requests, results, MCP output, diagnostics, or logs.
Relay commands are redelivered until acknowledged. Preserve stable command IDs and require host-side request de-duplication rather than weakening delivery to best-effort at-most-once behavior.
Never silently fall back to a test fixture, hosted evaluator, broader host profile, or trusted local runtime.
Treat hara.execution-host/0-alpha and hara.mcp-pure/0-alpha as Hara-owned contracts. Provisional copies in this repository must be replaced by generated or pinned upstream contracts under issue #3.
The deterministic fixture is transport test evidence only. It must remain disabled by default and identify itself as test-fixture.
Qualified calls invoke an already-loaded Var with transfer-safe arguments. Do not construct call source by concatenating arguments.
Unknown fields, versions, profiles, capabilities, command acknowledgements, generations, and lifecycle transitions fail closed.
Request cancellation must flow from context.mcpReq.signal through the gateway to the selected host. Do not replace cancellation with a fabricated successful terminal result.

Read the full file on GitHub · 41 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 · 41 lines · 550 tokens per session scan A 71d97d554ca9

Subscribe to this mod's changes

hara-mcp AGENTS.md is an instructions file published in the GitHub repository hara-lang/hara-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 550 tokens to every session, about $0.0022 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.

hara-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hara-mcp AGENTS.mdhara-lang/hara-mcp	Instructions file	0	2mo ago	Apache-2.0	A	550	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

hara-mcp: Instructions file for Codex