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/guepard-corp/qwery-core/agents-mdgit clone --depth 1 https://github.com/Guepard-Corp/qwery-coreWrote 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/guepard-corp/qwery-core/agents-md)<a href="https://agentmods.dev/instructions/guepard-corp/qwery-core/agents-md"><img src="https://agentmods.dev/badge/instructions/guepard-corp/qwery-core/agents-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 | $0.01904 | $0.01904 |
| Opus 5 | $0.00952 | $0.00952 |
| Sonnet 5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
qwery-core 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 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Strict rules for AI contributors
You are contributing to qwery-agent, an AI data analyst with a TUI. This file is the machine-oriented contract. README.md is for humans.
If you don't read this end-to-end, you will violate an invariant.
Decisions live in memory/ADR/decisions.md and memory/ADR/ui-decisions.md.
Architecture diagrams live in memory/diagrams/.
1. Non-negotiable invariants
These hold before anything else. Breaking them blocks a PR.
- Privacy boundary (ADR #28). The LLM never receives row-level data from any datasource.
runQueryaccepts aggregate-only SQL, single-row scalar output, validated locally.schemaanddescribeQueryreturn only column metadata.presentrenders results locally via Mustache + helpers — only{ ok, rowCount }goes upstream.- The privacy invariant test (
tooling/privacy-check.ts) is enforced in pre-push and CI.
- Tool minimalism (ADR-locked). Do not add a tool to the core agent unless it materially improves LLM reasoning. "Convenience" is not a justification.
- Hexagonal architecture (ADR #12).
domain/andapplication/never import fromadapters/orextensions/. Enforced bydependency-cruiser. - English only. All code, comments, identifiers, commit messages and documentation are in English. Chat with the user can be in other languages; the project file content cannot.
- No env vars for LLM config. Providers are configured via
/modelsin the TUI, stored at~/.qwery/config.json. Never re-introduce env-var fallbacks for provider credentials. - No code without unit tests. Every new module / feature / non-trivial change ships with
bun:testcoverage in the same turn. A code change without tests is incomplete. Cover happy path + at least one edge case + at least one failure mode. For LLM-dependent code, inject a stream function or use Vercel AI SDK'ssimulateReadableStream/simulateStreamingMiddlewarerather than calling real models.
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 · 165 lines · 1,904 tokens per session scan A d94579855005
qwery-core AGENTS.md is an instructions file published in the GitHub repository Guepard-Corp/qwery-core (134 stars, last pushed 1mo ago), licensed MIT. It adds 1,904 tokens to every session, about $0.0095 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
Addax AGENTS.md
AGENTS.md instructions for wgzhao/Addax, covering agents.md, 概述, 通用偏好, 编译 and 整体编译.
apple-health-mcp AGENTS.md
Instructions for neiltron/apple-health-mcp, covering repository guidance, project, validate changes, code map and invariants.
agent-skills AGENTS.md
Instructions for ClickHouse/agent-skills, covering agents.md, repository overview, repository structure, creating a new skill and directory structure.
dory AGENTS.md
AGENTS.md instructions for dorylab/dory, covering agents.md, product model, core source areas, commands and coding rules.
dory CLAUDE.md
Claude Code instructions for dorylab/dory, covering dory - claude code guidelines, project structure, package manager, shadcn/ui and dependency upgrades.
phpClickHouse CLAUDE.md
Instructions for smi2/phpClickHouse, covering claude.md — phpclickhouse, project overview, principles, architecture and key notes.