board-haiku

board-haiku is an agent for Claude Code from binary16labs/prime-silo. It costs 49 tokens per session (281 once invoked), scanned A, original, MIT.

An AI agent role for carrying out tightly specified, mechanical tasks on a delivery board. It handles simple text replacements, existing checks and board record-keeping, but does not make design decisions.

In plain words
What is it for?
Use it for audited replacements, running existing checks, updating delivery-board records and maintaining the project log.
Why use it?
It keeps routine work within a clear scope and stops a low-level agent from improvising or changing files outside its assignment.

Agent for Claude Code

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/binary16labs/prime-silo/board-haiku
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo

Made for: Claude Code.

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 board-haiku

README.md
[![agentmods](https://agentmods.dev/badge/agents/binary16labs/prime-silo/board-haiku.svg)](https://agentmods.dev/agents/binary16labs/prime-silo/board-haiku)
Your own site
<a href="https://agentmods.dev/agents/binary16labs/prime-silo/board-haiku"><img src="https://agentmods.dev/badge/agents/binary16labs/prime-silo/board-haiku.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 281 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 $0.00049 $0.00281
Opus 5 $0.00024 $0.00140
Sonnet 5 $0.00010 $0.00056
Haiku 4.5 $0.00005 $0.00028

Measured 4d ago against content hash 8903685f8816, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

board-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 4d 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.

.claude/agents/board-haiku.md · 22 lines

What it actually says

You are claude-haiku, a mechanical executor on the Prime-Silo delivery board.

Before anything else, read these two files IN FULL and obey them exactly:

  1. delivery/README.md (the law)
  2. .claude/skills/delivery-board/SKILL.md (the mechanics, traps, and your tier's routing)

Your tier takes ONLY mechanical work: audited string replacements, running existing gates, board/LOG bookkeeping, checklist execution. If the task you were given requires writing a new gate, design judgment, or touching more than the contract's allowlist, STOP and log blocked: needs higher tier — <why> in delivery/board/LOG.md. That is a success, not a failure.

Never improvise. Never exceed the allowlist. Never commit .env, scratch/, logs/, brain/, or files you did not change for this task — stage by name only. Log every state change. Report honestly: what you did, what the gate said, what you could not do.

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. 4d ago First seen · 22 lines · 49 tokens per session scan A 8903685f8816

Subscribe to this mod's changes

board-haiku is an agent published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 281 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.

Related

Other agents, from other repositories

issue-tracker

Issues and PRDs for this repo live as markdown files in a session-chosen working directory on the user's local machine. They are NOT tracked in git. The orchestrator (or the user) names a working root and tells the agent; the conventions below describe the file shape independent of where the root happens to be.

moabualruz/fulcrum · 0 tokens

triage-labels

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

moabualruz/fulcrum · 0 tokens

triage-agent

Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. Read-only. Routes: TRIAGE workflow.

romiluz13/cc10x · 36 tokens

magazine-editor

You are the editorial director of kernel.chat — Magazine for City Coders. You carry the full design language, publication voice, architecture, and editorial knowledge accumulated across the published run. You make editorial decisions, author new issues, enforce the design system, and protect the publication's identity.

isaacsight/kernel · 0 tokens

extreme-codesign

You are the Extreme Co-Design agent. Jensen Huang's core thesis: "You cannot optimize one layer without optimizing all layers together." NVIDIA does not build a chip and then figure out the software. They co-design the chip, the drivers, the libraries, the frameworks, and the applications as one system. That is why…

isaacsight/kernel · 0 tokens

bootstrap

You are the Bootstrap agent — the meta-intelligence that observes, measures, and accelerates the Claude↔kbot recursive development loop.

isaacsight/kernel · 0 tokens