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/lightdash/lightdash/agents-mdgit clone --depth 1 https://github.com/lightdash/lightdashWhat 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 | $0.00987 | $0.00987 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade B, and why
lightdash AGENTS.md scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo dockerd > /tmp/dockerd.log 2>&1 & 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 · 41 lines · 987 tokens per session scan B cdec94c952f6
lightdash AGENTS.md is an instructions file published in the GitHub repository lightdash/lightdash (6,105 stars, last pushed yesterday), with no licence file. It adds 987 tokens to every session, about $0.0049 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
evidence AGENTS.md
Instructions for evidence-dev/evidence, covering agents.md, this repo is a mirror, layout and scripts.
evidence CLAUDE.md
Instructions for evidence-dev/evidence, a project described as: Business intelligence as code: build fast, interactive data visualizations in SQL and markdown.
publisher AGENTS.md
Instructions for malloydata/publisher, covering working with malloy publisher, what you can do, 1. start the server first, 2. connect your agent and 3. the mcp tools.
publisher CLAUDE.md
Instructions for malloydata/publisher: Copyright (c) Credible Data Inc. SPDX-License-Identifier: MIT -->.
horizun-pbi-mcp AGENTS.md
AGENTS.md instructions for HorizunGroup/horizun-pbi-mcp, covering repository rules for agents, 1. before touching anything, 2. the mcp contract is untouchable, 3. invariants no phase can break and 4. real data: never enters git.
orionbelt-semantic-layer-mcp AGENTS.md
AGENTS.md instructions for ralforion/orionbelt-semantic-layer-mcp, covering agents.md, what this is, commands, architecture (the non-obvious parts) and version tracking & release discipline.