Borrowing it
Nothing to install: this file belongs to patriceckhart/zot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/patriceckhart/zot/main/AGENTS.mdgit clone --depth 1 https://github.com/patriceckhart/zotWrote 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/patriceckhart/zot/agents-md)<a href="https://agentmods.dev/instructions/patriceckhart/zot/agents-md"><img src="https://agentmods.dev/badge/instructions/patriceckhart/zot/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/patriceckhart/zot/agents-md"><img src="https://agentmods.dev/badge/instructions/patriceckhart/zot/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01909 | $0.01909 |
| Opus 5 | $0.00955 | $0.00955 |
| Sonnet 5 | $0.00382 | $0.00382 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
zot 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 9d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working Agreement for zot
This file defines how automated coding assistants should work in this repository. Treat it as a practical operating manual, not a substitute for reading the code.
Product intent
zot is a compact Go coding-agent harness. Changes should preserve its defining properties:
- one portable binary
- a provider-neutral agent engine
- a terminal UI without a framework dependency
- extensions that communicate through subprocess JSON-RPC
- predictable behavior on macOS, Linux, and Windows
- a small dependency and operational footprint
Prefer a narrow, explicit implementation over a generalized subsystem. New abstractions must earn their cost through a real boundary or repeated use.
Starting a task
Build context before editing:
- Inspect
git status --short. Existing modifications may belong to the user or another agent. - Locate and read every
AGENTS.mdthat governs the target path. - Read the owning implementation, nearby tests, and any user-facing documentation for the behavior.
- Reproduce reported failures when feasible. Record expected behavior separately from observed behavior.
- For GitHub work, inspect the issue or pull request with
ghif it is available. Do not change branches merely to review a pull request.
Do not use a search result or one function as a complete model of a feature. Follow calls across package boundaries and inspect persisted or streamed representations when relevant.
Code ownership map
Put behavior in the package that owns the concern:
| Area | Responsibility |
|---|---|
packages/core |
Agent loop, messages, tool contracts, events, confirmation, sessions, compaction |
packages/provider |
Provider clients, wire formats, streaming, retries, model metadata and discovery |
packages/provider/auth |
Login flows, credential lookup, refresh, and storage |
packages/agent |
CLI configuration, model selection, runtime assembly, RPC, and zotfiles |
packages/agent/modes |
Interactive, print, JSON, dialog, bot, and Telegram interfaces |
packages/agent/extensions |
Extension process lifecycle and host integration |
packages/agent/extproto |
Extension wire protocol |
packages/agent/ext |
Public extension SDK |
packages/agent/skills |
Skill discovery and loading |
packages/agent/swarm |
Background-agent state, supervision, and persistence |
packages/agent/tools |
Built-in tools, permission checks, and jail behavior |
packages/tui |
Terminal input, layout, rendering, markdown, themes, and images |
packages/ignore |
Ignore-pattern matching |
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.
- 9d ago First seen · 192 lines · 1,909 tokens per session scan A aa502c76d432
zot AGENTS.md is an instructions file published in the GitHub repository patriceckhart/zot (335 stars, last pushed today), licensed MIT. It adds 1,909 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.