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/mocaos/cortex-app/claude-mdgit clone --depth 1 https://github.com/mocaOS/cortex-appWrote 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/mocaos/cortex-app/claude-md)<a href="https://agentmods.dev/instructions/mocaos/cortex-app/claude-md"><img src="https://agentmods.dev/badge/instructions/mocaos/cortex-app/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 | $0.02278 | $0.02278 |
| Opus 5 | $0.01139 | $0.01139 |
| Sonnet 5 | $0.00456 | $0.00456 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
cortex-app 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 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Cortex is an agentic knowledge base that ingests documents, extracts entities/relationships via LLMs, builds a Neo4j knowledge graph, and exposes it through a FastAPI REST API for RAG applications. Next.js 15 frontend for search, Q&A, graph exploration, and document management.
Navigation Map
| File | Description |
|---|---|
.claude/architecture.md |
Tech stack, backend service map, frontend routes & components |
.claude/environment.md |
All 160+ env vars grouped by concern (DB, LLMs, features, skills, auth) |
.claude/development.md |
Docker/local dev commands, Neo4j setup, deployment (Coolify, Dokploy, standalone) |
.claude/design-system.md |
Design tokens, visual principles, .impeccable.md reference |
.claude/maintenance.md |
Doc sync rules for README, documentation/, handbook/, design-system/, .claude/ |
.claude/frontend-patterns.md |
Explore browsers, graph expansion, chat rendering, source modal, pagination |
.claude/domain/document-pipeline.md |
Upload → Docling → chunking → embedding → extraction → image analysis |
.claude/domain/relationships.md |
Per-chunk extraction, batch analysis (Phase 1/2), ERR, multi-round, batching |
.claude/domain/entities.md |
Fuzzy resolution, dedup (rapidfuzz), merging, editing, search, type normalization |
.claude/domain/communities.md |
Leiden/Louvain detection, summarization, staleness tracking |
.claude/domain/knowledge-graph-ui.md |
3-step pipeline page, staleness, regeneration flow, image awareness |
.claude/domain/rag-pipeline.md |
Researcher/writer agents, tools, speed/quality modes, hybrid search |
.claude/domain/skills.md |
AgentSkills standard, auto-activation, http_request, config wizard |
.claude/domain/admin-features.md |
System reset, library import/export, bulk download, API key management |
.claude/domain/git-integration.md |
Git connector (GitHub/GitLab/Gitea): provider abstraction, incremental sync engine, document provenance, git_repo write tool, scheduled polling |
.claude/domain/web-crawl.md |
MDHarvest powered by Crawl4ai — web→markdown harvesting via a (self-hosted or shared) crawl4ai service, crawl client, Web Import endpoints/UI, multi-tenant privacy model |
.claude/domain/x402.md |
x402 pay-per-query monetization — env flag → runtime config → verification, monetized public keys (read-only + endpoint allowlist), settle-before-serve payment gate, vendor-agnostic facilitator client, earnings |
.claude/domain/apps.md |
In-instance app hosting (ENABLE_APPS) — zip install, minted per-app keys, sandboxed iframe + app tokens, endpoint-allowlisted SSE-safe proxy, share-link grants; ecosystem plan in cortex-registry/ECOSYSTEM.md |
.claude/domain/observability.md |
Langfuse LLM tracing & cost — env-driven activation, OpenAI client factory, agentic-trace grouping (observed_trace/traced_sse), manual records for Haystack embeddings + raw-httpx vision, streaming usage capture. GlitchTip error tracking (SENTRY_*): backend error_tracking.py, frontend @sentry/nextjs + source-map upload |
.claude/bench.md |
Bench harness (bench/) — LLM-stack benchmark orchestrator, model registry, safety backup, heuristics. Not yet publicly documented — keep changes scoped. |
.claude/qa.md |
QA & testing — backend pytest suite (.qa-venv, conftest fixtures, coverage map), live E2E harness (test_live_e2e*.py), canonical QA spreadsheet (qa/), defect log |
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.
- 4d ago First seen · 85 lines · 2,278 tokens per session scan A 565b04dcb01f
cortex-app CLAUDE.md is an instructions file published in the GitHub repository mocaOS/cortex-app (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 2,278 tokens to every session, about $0.0114 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.
Other instructions, from other repositories
graph-memory CLAUDE.md
Instructions for stevepridemore/graph-memory, covering graph memory, when to consult the graph, how to use it, writing to the graph during conversation and when to write (call graphrelate).
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
amfs CLAUDE.md
Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.
docmancer copilot-instructions.md
Instructions for docmancer/docmancer, covering docmancer, workflow and core commands.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.