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/johnzfitch/raley-bot/claude-mdgit clone --depth 1 https://github.com/johnzfitch/raley-botWrote 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/johnzfitch/raley-bot/claude-md)<a href="https://agentmods.dev/instructions/johnzfitch/raley-bot/claude-md"><img src="https://agentmods.dev/badge/instructions/johnzfitch/raley-bot/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 | $0.01211 | $0.01211 |
| Opus 5 | $0.00606 | $0.00606 |
| Sonnet 5 | $0.00242 | $0.00242 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
raley-bot CLAUDE.md scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
api.py -- curl subprocess HTTP, all store endpoints Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
The store runs F5 BIG-IP TLS fingerprinting that blocks every Python HTTP library. `subprocess.run(["curl", ...])` with list args passes because curl's TLS handshake matches browsers. This is load-bearing. Do not replace How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Raley doesn't shop for you. Raley shops with you.
Named after a person who makes grocery day feel less like a chore. Not the chain.
Commands
uv venv && source .venv/bin/activate
uv pip install -e ".[dev,login]"
pytest # 89 tests, <2s
pytest -v # verbose
pytest tests/test_reasoning.py # single module
pytest -k "brand" # by keyword
raley-bot login # browser auth
raley-mcp # MCP stdio server
All tests run in <2s. If a test takes >5s, something is hitting the network and that's a bug.
Architecture
Grocery shopping assistant wrapping a real store API. Searches products, compares unit prices, tracks price history in SQLite, manages coupons, builds carts from freeform grocery lists. Exposed as both a CLI (raley) and an MCP server (raley-mcp) for Claude Desktop.
Full details: docs/ARCHITECTURE.md -- dependency graph, data flow, DB schema, scoring table. Audit trail: docs/AUDIT.md -- what was broken, removed, and fixed.
Module Map
mcp_server.py -- 15 MCP tools, the main interface
api.py -- curl subprocess HTTP, all store endpoints
db.py -- SQLite WAL, price history, deal detection
reasoning.py -- heuristic scoring (NOT ml), purchase frequency
cart_builder.py -- grocery list parsing, value-sorted search
unit_pricing.py -- $/oz $/lb $/ml $/unit normalization
preferences.py -- loads ~/.config/raley-assistant/preferences.json
t1d.py -- T1D nutrition scoring, GI database
memory.py -- persistent shopping memory (T1D config, notes)
knowledge.py -- T1D reference book search
auth.py -- Helium/Selenium browser login
cookies.py -- session persistence, validation
cli.py -- Click + Rich, standalone from MCP
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 · 90 lines · 1,211 tokens per session scan A 1cc1f41ea36a
raley-bot CLAUDE.md is an instructions file published in the GitHub repository johnzfitch/raley-bot (1 stars, last pushed 2mo ago), licensed Unlicense. It adds 1,211 tokens to every session, about $0.0061 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Unity-MCP copilot-instructions.md
Copilot instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.
mcp-erpnext AGENTS.md
AGENTS.md instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
mcp-erpnext CLAUDE.md
Claude Code instructions for Casys-AI/mcp-erpnext: See AGENTS.md for all repository guidelines, architecture, conventions, and task recipes.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
powerbi-mcp CLAUDE.md
Instructions for sulaiman013/powerbi-mcp, covering claude.md and developer notes.