jinn AGENTS.md

jinn AGENTS.md is an instructions file for Codex, OpenCode from hristo2612/jinn. It costs 3,748 tokens per session, scanned A, original, MIT.

Repository instructions for Jinn, a pnpm and Turbo monorepo containing a gateway service, command-line tool, web dashboard, and shared event definitions.

In plain words
What is it for?
Use them when modifying Jinn to check repository structure, avoid publishing personal data, and run the required type checks, linting, tests, and builds.
Why use it?
They set rules for privacy, code quality, testing, and changes that affect the public package and its users.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

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/hristo2612/jinn/agents-md
Clone the repo
git clone --depth 1 https://github.com/hristo2612/jinn

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.

agentmods badge for jinn AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hristo2612/jinn/agents-md.svg)](https://agentmods.dev/instructions/hristo2612/jinn/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hristo2612/jinn/agents-md"><img src="https://agentmods.dev/badge/instructions/hristo2612/jinn/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,748 This file is loaded in full into every session.
When invoked 3,748 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 5.1 $0.03748 $0.03748
Opus 5 $0.01874 $0.01874
Sonnet 5 $0.00750 $0.00750
Haiku 4.5 $0.00375 $0.00375

Measured 6d ago against content hash 18deef36f478, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

jinn 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 6d 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 · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

The review rubric for this repository. It applies to humans and to agents; a reviewer may fault a change against a rule written here, and an author may push back on a finding that cites nothing here and no stated requirement.

Jinn is a pnpm + turbo monorepo: a gateway daemon and CLI (packages/jinn), a React web dashboard (packages/web), and a shared event contract (packages/gateway-events).

This repository is public and publishes to npm. Everything under packages/** reaches strangers, including packages/jinn/template/** (the files that seed a new user's instance home) and test files (they compile into dist/ and ship in the tarball). No real names, client names, emails, API keys, chat workspace IDs, or absolute home-directory paths go anywhere in this tree. Anything that must be personal is read at runtime from the instance home, never hardcoded. packages/jinn/src/shared/__tests__/privacy-guard.test.ts:9 scans the shipped trees and fails the build on a match.

Four commands gate a change, and each one is a CI job in .github/workflows/ci.yml:

pnpm typecheck   # ci.yml:27
pnpm lint        # ci.yml:39
pnpm test        # ci.yml:81 — ubuntu and windows, both required
pnpm build       # ci.yml:109

1. Verify the premise

A ticket describes what someone believed at the time they wrote it. Before you fix it, establish that it is still true.

No fix ships without three things:

  1. A reproduction on current main — the command, and its real output.
  2. The exact file:line where the bug manifests. Not the area. The line.
  3. Evidence that your change alters that line's behaviour.

A claim of impossibility needs a red test. If you say a hole is now closed, a state is unreachable, or an input can no longer forge a result, write the test, revert your fix, and watch it fail. Put the fix back and watch it pass. Without that round trip you have written a test that asserts your implementation exists — which is indistinguishable from one that asserts the hole is shut, right up until the day it isn't.

Read the full file on GitHub · 281 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.

  1. 6d ago First seen · 281 lines · 3,748 tokens per session scan A 18deef36f478

Subscribe to this mod's changes

jinn AGENTS.md is an instructions file published in the GitHub repository hristo2612/jinn (314 stars, last pushed 6d ago), licensed MIT. It adds 3,748 tokens to every session, about $0.0187 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 2026-08-30.

Related

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens