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/deepset-ai/haystack/claude-mdgit clone --depth 1 https://github.com/deepset-ai/haystackWhat 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 | $0.00026 | $0.00026 |
| Opus 5 | $0.00013 | $0.00013 |
| Sonnet 5 | $0.00005 | $0.00005 |
| Haiku 4.5 | $0.00003 | $0.00003 |
Grade A, and why
haystack 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 2d 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.
What it actually says
CLAUDE.md
Before you start working on this repository, read the AGENTS.md file and follow all the instructions.
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.
- 2d ago First seen · 4 lines · 26 tokens per session scan A d99dd72013b7
haystack CLAUDE.md is an instructions file published in the GitHub repository deepset-ai/haystack (26,390 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session, about $0.0001 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
kernel-lore-mcp CLAUDE.md
Claude Code instructions for mjbommar/kernel-lore-mcp, covering kernel-lore-mcp — project state, pointers, standards, original goal and non-negotiable product constraints.
weaviate CLAUDE.md
Claude Code instructions for weaviate/weaviate, covering claude.md, no bug is ever out of scope, build & run, build the binary (cgoenabled=0, static linking) and build debug binary (with delve support).
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
mcp-memory-service CLAUDE.md
Instructions for doobidoo/mcp-memory-service, covering claude.md, non-negotiables (hard rules), critical directives, operational rules and auto-save learnings.
stride-gpt AGENTS.md
Instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
CORAL AGENTS.md
Instructions for Human-Agent-Society/CORAL, covering agents.md — ai-assisted contributions to coral, 1. human accountability, 2. scope discipline, 3. duplicate-work checks and 4. keep agent guidance synchronized.