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/orgmentem/zotio/agents-mdgit clone --depth 1 https://github.com/OrgMentem/zotioWrote 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/orgmentem/zotio/agents-md)<a href="https://agentmods.dev/instructions/orgmentem/zotio/agents-md"><img src="https://agentmods.dev/badge/instructions/orgmentem/zotio/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 | $0.02494 | $0.02494 |
| Opus 5 | $0.01247 | $0.01247 |
| Sonnet 5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
zotio 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zotio Agents Guide
This repo was bootstrapped by CLI Printing Press in 2026-05, but it has been hand-maintained since. The generator was retired on 2026-07-08: there is no regeneration path, and systemic fixes no longer route upstream first.
Local Operating Contract
Start by asking the generated CLI for current runtime truth:
zotio doctor --json
zotio agent-context --pretty
Use runtime discovery instead of relying on a copied command list:
zotio which "<capability>" --json
zotio <command> --help
Add --agent to command invocations for JSON, compact output, non-interactive defaults, no color, and confirmation-safe scripting:
zotio <command> --agent
Before running an unfamiliar command that may mutate remote state, inspect its help and prefer a dry run:
zotio <command> --help
zotio <command> --dry-run --agent
Use --yes --no-input only after the target, arguments, and side effects are clear.
For install, auth, examples, and longer product guidance, read README.md and SKILL.md. This file intentionally stays small so repo-local agents get invariant local guidance without duplicating the generated docs.
For CI, the zotio-action GitHub Action (marketplace) packages install → sync → gate on library health exit codes; see docs/guide/ci.md.
Before cutting a release (tagging v*), read dev/releasing.md — release flow, version/breaking-change decisions, validation checklist, and footguns. When the release coordinates with papio (the acquisition-side sister project), also read ~/@dev/papio/.agents/skills/papio-release/SKILL.md: papio enforces a minimum-zotio-version floor and its release order depends on whether that floor moved.
Dependency Updates
Two invariants that a routine go get -u breaks silently. Both are gated, so make ci catches them before CI does.
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.
- 3d ago First seen · 77 lines · 2,494 tokens per session scan A 8679ee8f0ba9
zotio AGENTS.md is an instructions file published in the GitHub repository OrgMentem/zotio (2 stars, last pushed 3d ago), licensed MIT. It adds 2,494 tokens to every session, about $0.0125 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
zotkit AGENTS.md
Instructions for oldantique/zotkit, covering instructions for ai agents, 1. install, 2. configure (interactive — involve the user), 3. operate and safety rules (non-negotiable).
zotkit CLAUDE.md
Instructions for oldantique/zotkit, covering development context (for agent sessions in this repo), scope, cross-session routing, releasing and tests.
DeepPaperNote AGENTS.md
Instructions for 917Dhj/DeepPaperNote, covering deeppapernote agent guide, repository purpose, canonical sources, non-negotiable product invariants and repository structure.
AI-Powered-Literature-Review-Skills AGENTS.md
Instructions for stephenlzc/AI-Powered-Literature-Review-Skills, covering agents.md - literature reviewer skill, 项目概述, 核心特性, 技术栈 and 项目结构.
zotero-zotadata AGENTS.md
Instructions for ydeng11/zotero-zotadata, covering agents.md, role, technology constraints, typescript only and styling with tailwind css.
mktero AGENTS.md
Instructions for tenglvjun/mktero, covering agents.md, project overview, commands, repository map and architecture and runtime rules.