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/peaky8linders/claude-cortex/claude-mdgit clone --depth 1 https://github.com/Peaky8linders/claude-cortexWrote 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/peaky8linders/claude-cortex/claude-md)<a href="https://agentmods.dev/instructions/peaky8linders/claude-cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/peaky8linders/claude-cortex/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 | $0.01122 | $0.01122 |
| Opus 5 | $0.00561 | $0.00561 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
claude-cortex 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Commands
# Brainiac (Python — semantic graph engine)
pip install -e . # Install in dev mode
cd ~/.claude/knowledge && python -m brainiac stats # Graph overview
cd ~/.claude/knowledge && python -m brainiac search "query"
# Cortex (TypeScript — hook processor + MCP dashboard)
cd cortex && npm install && npm run build
cd cortex && npm test
# ContextScore (Python — analyzers + snapshot + HTTP API)
cd contextscore && pip install -e .
cd contextscore && pytest tests/ -v
Architecture
| Product | Language | Purpose |
|---|---|---|
brainiac/ |
Python | Semantic embedding engine, graph persistence, CLI |
cortex/ |
TypeScript | Hook processor, knowledge graph engine, MCP dashboard server |
contextscore/ |
Python | 7 analyzers, snapshot/recovery, HTTP API |
Plugin Structure
.claude-plugin/plugin.json — Plugin manifest
.claude/settings.json — Team permissions (committed)
.claude/rules/ — Path-scoped instruction modules
.claude/commands/ — 14 slash commands (learn, hypothesis, cortex-*, ralph-*, etc.)
.claude/skills/cortex/ — Auto-invoked cortex advisor + support docs (SKILL.md, GRAPH_SCHEMA.md, QUALITY_DIMENSIONS.md)
.claude/agents/ — cortex-advisor, graph-maintainer (haiku), work-evaluator (sonnet)
.mcp.json — MCP server registration (cortex-dashboard)
hooks/hooks.json — Hook wiring (5 events: SessionStart, PostToolUse, PreCompact, PostCompact, Stop)
hooks/scripts/ — Shell hook handlers
MCP Dashboard Tools
cortex_token_timeline— Token consumption time-series with spike detectioncortex_activity_map— Gantt-like skill/hook/tool activation timelinecortex_quality_heatmap— 7-dimension context quality radarcortex_graph_explorer— Interactive knowledge graphcortex_dashboard— Unified session dashboard with KPIs, charts, cost breakdown, and cross-session trends
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 · 106 lines · 1,122 tokens per session scan A a2e62f465da0
claude-cortex CLAUDE.md is an instructions file published in the GitHub repository Peaky8linders/claude-cortex (11 stars, last pushed 2mo ago), licensed MIT. It adds 1,122 tokens to every session, about $0.0056 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).