kontext-engine: Instructions file for Codex

AGENTS.md

kontext-engine AGENTS.md is an instructions file for Codex, OpenCode from LuciferMornens/kontext-engine. It costs 889 tokens per session, scanned A, original, Apache-2.0.

Project instructions for kontext-engine that define its goals, development commands, and a required process for gathering context before changing code. They emphasize small changes, correctness, and tests.

In plain words
What is it for?
Working on the project, finding affected files and existing patterns, planning changes, and running its npm-based checks.
Why use it?
They help a coding agent understand the existing project before editing it and verify changes with linting, type checks, and tests.

Instructions file for CodexOpenCode

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

This is LuciferMornens/kontext-engine's own configuration. It tells Codex and OpenCode how to work on kontext-engine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kontext-engine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LuciferMornens/kontext-engine. 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/LuciferMornens/kontext-engine/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/LuciferMornens/kontext-engine

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 kontext-engine AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lucifermornens/kontext-engine/agents-md/github.svg)](https://agentmods.dev/instructions/lucifermornens/kontext-engine/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lucifermornens/kontext-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/lucifermornens/kontext-engine/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.

agentmods 80×15 button for kontext-engine AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lucifermornens/kontext-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/lucifermornens/kontext-engine/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 889 This file is loaded in full into every session.
When invoked 889 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00889 $0.00889
Opus 5.5 $0.00356 $0.00356
Sonnet 5.5 $0.00178 $0.00178
Haiku 4.5 $0.00089 $0.00089

Measured 2mo ago against content hash 54cec3d1afc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kontext-engine 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

North star

Ship small, modular, production-ready changes with high-signal context and tests that gate progress. Correctness > speed.

Commands (keep updated)

Put real, copy-pastable commands here. If missing, discover them in README.md, package.json scripts, Makefile, or .github/workflows/*.

  • Install deps: npm install
  • Lint: npm run lint
  • Typecheck: npm run typecheck
  • Unit tests: npm run test
  • Integration/E2E tests: npm run test
  • Full local check (closest to CI): npm run check

1) Context engineering (mandatory before acting)

Before editing anything, gather and organize only the context needed to execute correctly.

Before starting any task

  • Understand scope
    • Read the relevant existing files first (don’t guess).
    • Identify existing patterns/utilities/conventions to follow.
    • Note dependencies and potential side effects.
  • Gather context
    • Which files/modules will be affected?
    • What existing code should be referenced or reused?
    • Are there similar implementations to mirror?
  • Plan the approach
    • Break work into discrete, verifiable steps.
    • Call out risks/failure points and how you’ll detect them.
  • Maintain focus
    • Keep working memory limited to task-relevant facts.
    • For long tasks: periodically summarize “what changed / what’s next”.
    • Record decisions that affect future work (short comments, docs, or ADR).

If requirements are unclear: ask a targeted question or propose a short plan—don’t invent requirements.


2) Modular architecture (default posture)

  • Prefer small, composable modules with single responsibility.
  • Keep boundaries explicit: clear public interfaces, minimal coupling.
  • Reuse existing utilities and patterns; avoid duplicating logic.
  • Localize change: avoid drive-by refactors unless required for correctness.
  • Prefer dependency direction that keeps core logic independent of frameworks/UI/IO.

3) Production-ready quality (no leftovers)

No “almost done” code. No shortcuts.

  • 🚫 No TODO, FIXME, “temporary” hacks, commented-out blocks, dead code.
  • 🚫 No debug logs/noisy prints left behind.
  • Handle errors and edge cases; validate inputs; preserve backward compatibility unless explicitly changing it.
  • Keep code readable: good names, small functions, consistent style, strict types where applicable.
  • Update docs/examples when behavior or APIs change.
  • Never introduce or leak secrets/PII; avoid logging sensitive data.

Read the full file on GitHub · 93 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. 2mo ago First seen · 93 lines · 889 tokens per session scan A 54cec3d1afc3

Subscribe to this mod's changes

kontext-engine AGENTS.md is an instructions file published in the GitHub repository LuciferMornens/kontext-engine (22 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 889 tokens to every session, about $0.0036 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.

Related

kontext-engine AGENTS.md compared with instructions from other repositories

kontext-engine AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kontext-engine AGENTS.mdLuciferMornens/kontext-engineInstructions file228mo agoApache-2.0A889Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode