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/barysiuk/duckrow/agents-mdgit clone --depth 1 https://github.com/barysiuk/duckrowWrote 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/barysiuk/duckrow/agents-md)<a href="https://agentmods.dev/instructions/barysiuk/duckrow/agents-md"><img src="https://agentmods.dev/badge/instructions/barysiuk/duckrow/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 | $0.02050 | $0.02050 |
| Opus 5 | $0.01025 | $0.01025 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
duckrow 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 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.
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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
duckrow is a Go CLI tool that manages AI agent skills across multiple project folders.
Project Structure
cmd/duckrow/ CLI entrypoint and integration tests
cmd/ Cobra command definitions (thin wrappers)
testdata/script/ testscript integration tests (.txtar files)
main.go Entrypoint
main_test.go TestMain + testscript runner + custom commands
internal/core/ Core library (zero UI dependencies)
asset/ Asset handler interfaces and implementations (skill, MCP, agent)
system/ System interfaces and implementations (7 systems)
auth.go Clone error classification, SSH/HTTPS hints
compat.go Legacy type adapters for backward compatibility
config.go Config management (~/.duckrow/)
env.go Environment variable resolution for MCP servers
folder.go Folder tracking
helpers.go Shared utility functions
lockfile.go Lock file v3 (unified assets array)
orchestrator.go Coordination layer for install/remove/scan
registry.go Private registry management (v1/v2 manifests)
source.go Source URL parsing
types.go Domain types
internal/tui/ Interactive terminal UI (Bubble Tea)
app.go Main TUI model, view routing, data loading
folder.go Folder view — skill list, preview, removal
install.go Install view — skill/MCP picking list
asset_wizard.go Asset install wizard (system selection, env vars)
wizard.go Shared wizard component
registry_wizard.go Registry add wizard
bookmarks.go Bookmarks view — folder switching
sidebar.go Sidebar panel — folder info, systems
tabs.go Tab bar component
statusbar.go Status bar (transient messages, spinner)
settings.go Settings view — registry management
confirm.go Confirmation dialog
clone_error.go Clone error handling with retry flow
items.go List item delegates for bubbles components
keys.go Keybinding definitions
theme.go Shared lipgloss styles and colors
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 · 213 lines · 2,050 tokens per session scan A 2209f1a5acc1
duckrow AGENTS.md is an instructions file published in the GitHub repository barysiuk/duckrow (9 stars, last pushed 2mo ago), licensed MIT. It adds 2,050 tokens to every session, about $0.0103 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.