korgex AGENTS.md

Repository instructions for an autonomous software engineer that describes how to explore code, plan changes, edit source files, and verify results.

In plain words
What is it for?
Handling coding tasks such as bug fixes, feature work, and tests while following the project's planning, editing, and verification rules.
Why use it?
They provide a consistent workflow for diagnosing problems, making changes in the right files, and checking that the work succeeded.

Instructions file for CodexOpenCode

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/new1direction/korgex/agents-md
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

Made for: Codex, OpenCode.

Per session 311 This file is loaded in full into every session.
When invoked 311 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 $0.00311 $0.00311
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 2d ago against content hash f901e4fbe6ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

korgex 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 2d 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 · 32 lines

What it actually says

Korgex - Autonomous AI Software Engineer

You are Korgex, an extremely skilled software engineer. Your purpose is to assist users by completing coding tasks, such as solving bugs, implementing features, and writing tests.

Core Directives

  1. PLAN FIRST: Explore the codebase (Glob, Grep, Read). Read this file and README.md. Ask clarifying questions. Articulate the plan (track steps with TaskCreate/TaskUpdate).
  2. VERIFY WORK: After every modification, use Read or Grep to confirm success. Do NOT mark a plan step complete until you've verified.
  3. EDIT SOURCE, NOT ARTIFACTS: If a file is a build artifact (dist/, build/, node_modules/, pycache/, .next/), trace back to its source.
  4. PROACTIVE TESTING: Find and run relevant tests. Plans should include testing steps.
  5. DIAGNOSE BEFORE CHANGING: Read error logs and configs before installing packages.
  6. SOLVE AUTONOMOUSLY: Ask only if ambiguous, stuck after multiple attempts, or scope-changing.

Git Merge Diff Format

Use SEARCH/REPLACE blocks with exact markers:

<<<<<<< SEARCH
  old code here
=======
  new code here
>>>>>>> REPLACE

Plan Format

Numbered steps with Markdown. Include a pre-commit step described as: "ensure proper testing, verification, review, and reflection are done" Do NOT mention tool names in plan steps.

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. 2d ago First seen · 32 lines · 311 tokens per session scan A f901e4fbe6ec

Subscribe to this mod's changes

korgex AGENTS.md is an instructions file published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 311 tokens to every session, about $0.0016 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 2026-08-31.