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/mrzdevcore/haira/claude-mdgit clone --depth 1 https://github.com/mrzdevcore/hairaWrote 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/mrzdevcore/haira/claude-md)<a href="https://agentmods.dev/instructions/mrzdevcore/haira/claude-md"><img src="https://agentmods.dev/badge/instructions/mrzdevcore/haira/claude-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 | $0.00221 | $0.00221 |
| Opus 5 | $0.00111 | $0.00111 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
haira CLAUDE.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.
What it actually says
Haira — Claude Code Instructions
Project Context
Primary languages: Go (main), TypeScript (frontend/tooling), Rust (occasional). When writing Go code, always verify API compatibility of external packages before using methods that may not exist in the version being used.
Debugging
When fixing bugs, verify the root cause before applying a fix. Do not assume naming mismatches or surface-level issues — check the actual database schema, config, or runtime behavior first.
UI/Frontend
For UI implementations, get the layout and positioning right on the first pass. Show clean, user-friendly labels instead of raw IDs. When implementing scrollable lists or virtual scroll, prefer div-based approaches over table row hacks.
Testing
When writing tests, use page object patterns and existing test abstractions rather than raw selectors. Check existing test files for conventions before writing new tests.
Writing & Communication
When the user asks for content drafting (emails, posts, replies), keep responses concise and incorporate ALL feedback in each iteration. Do not re-add details the user explicitly asked to remove.
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 · 22 lines · 221 tokens per session scan A aa6baafbaf18
haira CLAUDE.md is an instructions file published in the GitHub repository mrzdevcore/haira (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 221 tokens to every session, about $0.0011 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
deer-flow copilot-instructions.md
Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
cti-skills CLAUDE.md
Claude Code instructions for Liberty91LTD/cti-skills, covering cti-skills — claude code orientation, what's here, how to use the pack, tradecraft vocabularies and before committing.
agentfactory CLAUDE.md
Claude Code instructions for stempeck/agentfactory, covering agentfactory, build commands, dependencies, project structure and cli commands.
mavericks-os CLAUDE.md
Claude Code instructions for yahor-punko/mavericks-os, covering claude.md, what this repo is, session start, operational commands and architecture.
harikos.ai AGENTS.md
AGENTS.md instructions for ashyeager/harikos.ai, covering agents.md — harikos ai repository instructions, 1. read first, 2. product definition, 3. mvp means a real saas and 4. reality-only rule.