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/jiayuxu0/zipagent/agents-mdgit clone --depth 1 https://github.com/JiayuXu0/ZipAgentWrote 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/jiayuxu0/zipagent/agents-md)<a href="https://agentmods.dev/instructions/jiayuxu0/zipagent/agents-md"><img src="https://agentmods.dev/badge/instructions/jiayuxu0/zipagent/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 | $0.00504 | $0.00504 |
| Opus 5 | $0.00252 | $0.00252 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
ZipAgent 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Runtime code lives under src/zipagent/, with core agents in agent.py, execution control in runner.py, and supporting utilities across context.py, stream.py, and tool integrations (tool.py, mcp_tool.py). Shared prompts reside in src/zipagent/system.md. Tests mirror this layout inside tests/, while quick-start examples are in examples/ and contributor docs in docs/. Keep new assets alongside related modules to simplify discovery.
Build, Test & Development Commands
uv syncinstalls dependencies frompyproject.toml/uv.lock.uv run ruff check --fixformats and lint-fixes the codebase.uv run pyrightperforms strict type analysis.uv run pytestexecutes the test suite; add--cov=zipagent --cov-report=term-missingto inspect coverage.uv build(orhatch build) produces distributable packages when preparing releases.
Coding Style & Naming Conventions
Adhere to PEP 8 with four-space indentation, 79-character lines, and double quotes. Favor explicit type hints and Pydantic dataclass-style models. Name files and modules in snake_case, classes in PascalCase, and user-facing tool functions with descriptive verbs (e.g., fetch_weather_tool). Let Ruff handle import ordering and minor formatting fixes.
Testing Guidelines
Use pytest for all tests and place new cases beside the implementation under tests/. Name files test_*.py, leverage fixtures from tests/conftest.py, and mark async flows with @pytest.mark.asyncio. Maintain at least 75% coverage and ensure new failure modes receive regression tests.
Commit & Pull Request Guidelines
Commits follow Conventional Commit prefixes (feat:, fix:, docs:, etc.) with concise, sentence-case summaries. Squash WIP commits before opening a PR. Each PR should describe the motivation, link related issues, and include CLI output or screenshots for notable behaviors. Flag configuration or key-management changes explicitly for reviewer verification.
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 · 24 lines · 504 tokens per session scan A 858a245f3480
ZipAgent AGENTS.md is an instructions file published in the GitHub repository JiayuXu0/ZipAgent (110 stars, last pushed 1mo ago), licensed MIT. It adds 504 tokens to every session, about $0.0025 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
open-swe AGENTS.md
AGENTS.md instructions for langchain-ai/open-swe, covering agents.md, project, commands, architecture and entrypoints.
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, covering claude.md, project, commands, architecture and entrypoints.
LangBot AGENTS.md
Instructions for langbot-app/LangBot, covering agents.md, quick facts, essential commands, where to look and cross-repo sdk work.
dify AGENTS.md
AGENTS.md instructions for langgenius/dify, covering agents.md, repository gotchas and frontend workflow.
dify CLAUDE.md
Claude Code instructions for langgenius/dify, a project described as: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
flock AGENTS.md
Instructions for Onelevenvy/flock, covering agents.md, project overview, build & development commands, rust backend and build the cli.