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.
npx agentmods add instructions/lktiep/cortex-hub/claude-mdgit clone --depth 1 https://github.com/lktiep/cortex-hubWrote 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.
[](https://agentmods.dev/instructions/lktiep/cortex-hub/claude-md)<a href="https://agentmods.dev/instructions/lktiep/cortex-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/lktiep/cortex-hub/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00778 | $0.00778 |
| Opus 5 | $0.00389 | $0.00389 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
cortex-hub CLAUDE.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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Hub — Claude Code Instructions
Quick Start (MANDATORY)
Run /cs at the start of every conversation. This initializes the session, recalls context from previous sessions, and checks for conflicts. Editing is blocked until this completes.
If /cs is unavailable, run manually:
cortex_session_start(repo: "cortex-hub", mode: "development", agentId: "claude-code")cortex_knowledge_search(query: "session summary progress next session")cortex_memory_search(query: "session context decisions lessons")cortex_task_pickup()— check for assigned tasks
Tech Stack
Monorepo: pnpm + Turborepo. TypeScript strict. Hono API. Next.js 15 frontend. SQLite + Qdrant. Docker Compose.
Code Conventions
camelCase vars/functions, PascalCase types. @cortex/* path aliases. No any without comment.
How to Use Cortex Tools
Cortex tools replace grep/find with smarter alternatives. Use them naturally as part of your workflow:
Finding code
Use cortex_code_search instead of grep. It understands AST structure and returns focused results (~90% fewer tokens than raw grep). Fall back to grep only if it returns nothing.
Understanding code
cortex_code_context(name: "functionName")— see who calls it, what it calls, what imports itcortex_code_impact(target: "symbolName")— check blast radius before editingcortex_cypher(query: "MATCH ...")— advanced graph queries when you need exact relationships
Before editing shared files
Call cortex_changes(agentId: "claude-code", projectId: "<from session>") to check if another agent touched the same files.
When you hit an error
cortex_knowledge_search(query: "<error message>")— someone may have solved this alreadycortex_memory_search(query: "<error context>")— you may have seen this before- Fix the error
- If the fix was non-obvious:
cortex_knowledge_store(title: "<fix>", content: "<steps>")— save it so nobody debugs this again
Sharing what you learn
cortex_memory_store(content: "...")— personal recall for future sessions (decisions, gotchas, context)cortex_knowledge_store(title: "...", content: "...")— team-wide knowledge (bug fixes, patterns, architecture decisions)
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.
- 5d ago First seen · 73 lines · 778 tokens per session scan A e29a4e966970
cortex-hub CLAUDE.md is an instructions file published in the GitHub repository lktiep/cortex-hub (58 stars, last pushed 1mo ago), licensed MIT. It adds 778 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
sverklo CLAUDE.md
Instructions for sverklo/sverklo, covering sverklo development, using sverklo tools, project structure and build & test.
agentmako AGENTS.md
Instructions for drhalto/agentmako, covering mako mcp usage, operating model, default workflow, fast batches and freshness.
Memory-Recall AGENTS.md
AGENTS.md instructions for rebel0789/Memory-Recall, covering agents.md — operating manual for coding agents, mission, read order before changing code, current reality and implemented as a reference bootstrap.
Memory-Recall CLAUDE.md
Claude Code instructions for rebel0789/Memory-Recall: Read and follow AGENTS.md and ASSIGNTOAGENT.md. Run npm run status; only run npm run task -- when status names a next task. This file intentionally does not duplicate the canonical instructions.
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.