What is kheish AGENTS.md?

Operating instructions for Kheish, covering its daemon, command-line tools, HTTP API, sessions, tasks, and provider integrations. They explain repository basics and rules for validating changes in the real running system.

Running and debugging the daemon, validating CLI and API behaviour, testing fresh sessions and state directories, and maintaining provider-neutral code where possible.

They help agents avoid stale session data and misleading tests when working on a service with multiple providers. The guide clarifies where the source of truth is and how to test behaviour safely.

How graniet/kheish configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to graniet/kheish. 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/graniet/kheish/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/graniet/kheish

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/graniet/kheish/agents-md/github.svg)](https://agentmods.dev/instructions/graniet/kheish/agents-md)

Your own site

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

Per session 4,148 This file is loaded in full into every session.

When invoked 4,148 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	$0.04148	$0.04148
Opus 5.5	$0.01659	$0.01659
Sonnet 5.5	$0.00830	$0.00830
Haiku 4.5	$0.00415	$0.00415

Measured 2mo ago against content hash 625f39a4936d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kheish 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 · 617 lines

How it starts

The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kheish Operator Guide

This file is for future agent instances working inside kheish/.

Read this first when you need to change code, run the daemon, validate behavior on real providers, or debug a broken session.

This is an operational guide, not a full architecture spec.

Working Rules

Treat the daemon as the source of truth.
Prefer the real CLI and HTTP API over direct inspection of JSON state files.
Use fresh --state-root values for real validation.
Use fresh sessions for E2E tests.
Validate on the real daemon, not only with unit tests.
Keep examples and paths portable. This repository may be cloned anywhere.
When behavior differs across providers, keep the abstraction provider-neutral unless the provider wire format truly requires divergence.
Do not infer product behavior from stale sessions created by an older daemon build.

Repository Basics

Repository root:

the directory that contains this AGENTS.md

Important files:

.env
Cargo.toml
README.md
AGENTS.md

Most active crates:

crates/kheish-daemon: daemon HTTP API, CLI integration, run/session/task control plane
crates/kheish-runtime: provider drivers, prompt building, permissions, runtime assembly
crates/kheish-core: engine loop, compaction, hook integration
crates/kheish-coding-tools: built-in tools such as read_file, write_file, bash, web_fetch, web_search
crates/kheish-mcp: MCP loading, config import, tool/resource adaptation
crates/kheish-agent: agent orchestration, snapshots, sidechains, mailbox
crates/kheish-types: shared data contracts

Important old state roots that may still exist in this repo:

.kheish-daemon
.kheish-daemon2
.kheish-daemon-fix
.kheish-daemon-fix2

Do not assume the daemon you are talking to uses the state root you expect. Always be explicit.

Environment

Load provider keys before live testing:

cd "$(git rev-parse --show-toplevel)"
set -a
source .env
set +a

Supported providers in normal operation:

anthropic
google
openai
openrouter
xai

Read the full file on GitHub · 617 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 · 617 lines · 4,148 tokens per session scan A 625f39a4936d

Subscribe to this mod's changes

kheish AGENTS.md is an instructions file published in the GitHub repository graniet/kheish (213 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 4,148 tokens to every session, about $0.0166 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 2026-08-30.

agent ai ai-agent ai-agents anthropic framework

kheish AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kheish AGENTS.mdgraniet/kheish	Instructions file	213	3mo ago	Apache-2.0	A	4,148	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	today	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

kheish: Instructions file for Codex