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/jonpspri/databeak/agents-mdgit clone --depth 1 https://github.com/jonpspri/databeakWhat 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 | $0.01606 | $0.01606 |
| Opus 5 | $0.00803 | $0.00803 |
| Sonnet 5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
databeak AGENTS.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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 247 lines · 1,606 tokens per session scan A d0dcd7b1043a
databeak AGENTS.md is an instructions file published in the GitHub repository jonpspri/databeak (2 stars, last pushed 4mo ago), with no licence file. It adds 1,606 tokens to every session, about $0.0080 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
sq AGENTS.md
Instructions for neilotoole/sq, covering agents.md, about sq, key documents, common commands and conventions.
sq CLAUDE.md
Instructions for neilotoole/sq: Claude Code entry point for this repo. Shared rules live in AGENTS.md.
dbcrust CLAUDE.md
Instructions for clement-tourriere/dbcrust, covering claude.md, build commands, python bindings, gui (tauri) and module map.
dbcrust AGENTS.md
Instructions for clement-tourriere/dbcrust, covering agents.md - development guide for dbcrust, build/lint/test commands, core build commands, install bun-managed gui dependencies and build the project (development).
qsv CLAUDE.md
Claude Code instructions for dathere/qsv, covering claude.md, general rules, documentation, tools & commands and workflow requirements.
comma copilot-instructions.md
Copilot instructions for comma-csv/comma, covering copilot instructions for comma, build, test, and lint commands, install dependencies for the base gemfile, install all appraisal gemfiles used by ci and build the gem.