cortex-hub AGENTS.md

cortex-hub AGENTS.md is an instructions file for Codex, OpenCode from lktiep/cortex-hub. It costs 1,093 tokens per session, scanned A, original, MIT.

An agent guide for working on Cortex Hub, including its session routine and code-understanding tools.

In plain words
What is it for?
Use it to begin and resume development sessions, search the codebase, understand symbols, inspect affected areas, review changes, and search stored project knowledge.
Why use it?
It helps coding agents recover previous context, check for new changes and assigned work, and assess risks before editing. This reduces duplicated investigation and unexpected breakage.

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/lktiep/cortex-hub/agents-md
Clone the repo
git clone --depth 1 https://github.com/lktiep/cortex-hub

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 cortex-hub AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lktiep/cortex-hub/agents-md.svg)](https://agentmods.dev/instructions/lktiep/cortex-hub/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lktiep/cortex-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/lktiep/cortex-hub/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,093 This file is loaded in full into every session.
When invoked 1,093 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 $0.01093 $0.01093
Opus 5 $0.00547 $0.00547
Sonnet 5 $0.00219 $0.00219
Haiku 4.5 $0.00109 $0.00109

Measured 4d ago against content hash 9591c811ad72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-hub 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 4d 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cortex Hub — Agent Guidelines

Current Phase: 6 (Polish, docs, testing, GA release)


Session Lifecycle

Start

  1. cortex_session_start({ repo: "<repo URL>", mode: "development", agentId: "<your id>" }) — save the returned sessionId
  2. cortex_knowledge_search + cortex_memory_search — recall what happened last session
  3. cortex_task_pickup() — check for Conductor tasks assigned to you
  4. If recentChanges.count > 0git pull before editing

During Work

Use cortex tools as your primary workflow — they're faster, more focused, and save tokens compared to grep/find.

What you need Tool Why it's better
Find code cortex_code_search AST-aware, returns focused results (~90% fewer tokens than grep)
Understand a symbol cortex_code_context Shows callers, callees, imports, process participation
Check blast radius cortex_code_impact Know what breaks before you edit
Pre-commit risk cortex_detect_changes Affected symbols + risk rating
Graph queries cortex_cypher Direct Cypher on the knowledge graph
Known solutions cortex_knowledge_search Search before debugging from scratch
Past decisions cortex_memory_search Recall what you or other agents learned
Save a fix cortex_knowledge_store Team-wide — so nobody debugs this twice
Save context cortex_memory_store Personal recall for future sessions
Other agents' changes cortex_changes Check before editing shared files
Tool effectiveness cortex_tool_stats Usage analytics and success rates

Discovery order (try in this order before falling back to grep): memory_searchknowledge_searchcode_searchcode_contextcode_impact → grep/find

Bug protocol: search knowledge/memory first → fix → store non-obvious fixes via knowledge_store.

End

  1. Verify: pnpm build && pnpm typecheck && pnpm lint
  2. cortex_quality_report — report gate results
  3. cortex_memory_store — persist session context (what was done, decisions, next steps)
  4. cortex_session_end(sessionId, summary) — closes session + auto-saves summary as searchable memory

Read the full file on GitHub · 107 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. 4d ago First seen · 107 lines · 1,093 tokens per session scan A 9591c811ad72

Subscribe to this mod's changes

cortex-hub AGENTS.md is an instructions file published in the GitHub repository lktiep/cortex-hub (58 stars, last pushed 1mo ago), licensed MIT. It adds 1,093 tokens to every session, about $0.0055 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.