haiku

haiku is an agent for coding agents from rileyhilliard/agentrc. It costs 41 tokens per session (191 once invoked), scanned A, original, MIT.

A small task-running agent that carries out detailed instructions passed to it by other commands. It is intended for delegated work rather than direct use by people.

In plain words
What is it for?
Executing simple delegated tasks from commands such as creating commits, running tests, or preparing pull requests, when another command provides the instructions.
Why use it?
It handles clearly defined tasks consistently and reports what happened without adding unrelated work. The input does not specify particular coding or automation capabilities.

Agent

Install

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.

agentmods
npx agentmods add agents/rileyhilliard/agentrc/haiku
Clone the repo
git clone --depth 1 https://github.com/rileyhilliard/agentrc

Wrote 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.

agentmods badge for haiku

README.md
[![agentmods](https://agentmods.dev/badge/agents/rileyhilliard/agentrc/haiku.svg)](https://agentmods.dev/agents/rileyhilliard/agentrc/haiku)
Your own site
<a href="https://agentmods.dev/agents/rileyhilliard/agentrc/haiku"><img src="https://agentmods.dev/badge/agents/rileyhilliard/agentrc/haiku.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 191 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00191
Opus 5 $0.00020 $0.00096
Sonnet 5 $0.00008 $0.00038
Haiku 4.5 $0.00004 $0.00019

Measured 3d ago against content hash 156cbb9a4765, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

haiku 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.

.agentrc/agents/haiku.md · 23 lines

What it actually says

You are a task executor that receives detailed instructions from calling commands. Your job is to follow those instructions precisely and efficiently.

How You Work

Commands delegate simple, well-defined tasks to you along with specific instructions. You execute the task according to those instructions and report results back.

Guidelines

  • Follow the provided instructions exactly
  • Use only the tools necessary for the task
  • Report results clearly and concisely
  • If something goes wrong, provide a clear error description
  • Don't add extra steps or improvements unless instructed
Changes

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.

  1. 3d ago First seen · 23 lines · 41 tokens per session scan A 156cbb9a4765

Subscribe to this mod's changes

haiku is an agent published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 191 once invoked, about $0.0002 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.