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/vinikjkkj/zapo/agents-mdgit clone --depth 1 https://github.com/vinikjkkj/zapoWrote 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/vinikjkkj/zapo/agents-md)<a href="https://agentmods.dev/instructions/vinikjkkj/zapo/agents-md"><img src="https://agentmods.dev/badge/instructions/vinikjkkj/zapo/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 | $0.12795 | $0.12795 |
| Opus 5 | $0.06398 | $0.06398 |
| Sonnet 5 | $0.02559 | $0.02559 |
| Haiku 4.5 | $0.01280 | $0.01280 |
Grade A, and why
zapo 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 — 962 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md – Development Guide for zapo
Living guide for implementing features in this repository. Keep this file aligned with the real codebase.
1. Non-Negotiable Principles
| Principle | Meaning |
|---|---|
index-first |
Validate protocol behavior against wa-web/ (and wa-mob/ for mobile-specific flows) before implementation. Do not invent tags, attrs, namespaces, or flows. |
performance-first |
Optimize for low CPU, low RAM, and low allocations. Use zero-copy patterns in hot paths. |
async-first |
I/O and network paths must be async. Crypto follows the rule only where benchmarks justify it: X25519/Ed25519 and pbkdf2 stay async (libuv thread pool wins); hashes, AES, HMAC, HKDF are sync (the thread-pool hop costs more than the op). Public APIs should return Promise<T> when work is async. |
no-overengineering |
Avoid abstraction layers without concrete gains. Keep code direct and easy to maintain. |
real-flow-only |
Validate protocol features with real CLI/flow tests, not mock-only behavior. |
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 · 962 lines · 12,795 tokens per session scan A 5c19b74d660a
zapo AGENTS.md is an instructions file published in the GitHub repository vinikjkkj/zapo (210 stars, last pushed 5d ago), licensed MIT. It adds 12,795 tokens to every session, about $0.0640 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
platform AGENTS.md
AGENTS.md instructions for doka-guide/platform, covering agents.md — как работать с платформой доки, 1. правила работы, сначала подумай, потом пиши, минимум кода and правки хирургические.
claude-code-statusline AGENTS.md
Instructions for ilia-pluzhnikov/claude-code-statusline, covering claude-code-statusline, project shape, rules for contributors (and ai agents), editing this file and testing.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).
SoDam-WikiMate AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate 작업 규칙 (크로스툴 — claude code · codex · gemini 공용), 문체, 자동 동작 (자연어 트리거 — 강제 호출 불필요), 접근 규칙 (자동 감지 — 특정 도구에 한정하지 않음) and obsidian 규칙.
node-express-boilerplate typescript-assertions.instructions.md
Use when editing TypeScript in src to avoid assertion-related lint/type regressions after merges. Prefer narrowing, type guards, satisfies, and as const/typeof over unsafe casts.
hal-9000 AGENTS.md
Instructions for vinta/hal-9000, covering agents.md, commands, gotchas, external tool documentation and context7 library ids.