board-ciso

board-ciso is an agent for Claude Code from l3a0/claude-plugins. It costs 50 tokens per session (1,861 once invoked), scanned A, original, MIT.

A security-focused board seat for a one-person venture. It checks who can access the venture's money, accounts, data, and login credentials.

In plain words
What is it for?
Use it during a board sitting to review where keys and credentials are stored, what permissions they have, who can withdraw money, and how account recovery is protected.
Why use it?
It reduces the chance that stolen or overly broad credentials let someone withdraw funds, change payment settings, or access sensitive data. It favors stronger access controls over convenience.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Claude Code.

Part of the l3a0 plugin — 2 skills, 11 agents, 1 hook shipped together

Good fit Use it during a board sitting to review where keys and credentials are stored, what permissions they have, who can withdraw money, and how account recovery is protected.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/l3a0/claude-plugins/board-ciso
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.

Clone the repo
git clone --depth 1 https://github.com/l3a0/claude-plugins

Made for: Claude Code.

Or install l3a0, the plugin that ships this one along with the rest of its 2 skills, 11 agents, 1 hook.

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-ciso

README.md
[![agentmods](https://agentmods.dev/badge/agents/l3a0/claude-plugins/board-ciso/github.svg)](https://agentmods.dev/agents/l3a0/claude-plugins/board-ciso)
Your own site
<a href="https://agentmods.dev/agents/l3a0/claude-plugins/board-ciso"><img src="https://agentmods.dev/badge/agents/l3a0/claude-plugins/board-ciso/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for board-ciso

Your own site · 80×15
<a href="https://agentmods.dev/agents/l3a0/claude-plugins/board-ciso"><img src="https://agentmods.dev/badge/agents/l3a0/claude-plugins/board-ciso.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,861 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.01861
Opus 5.5 $0.00020 $0.00744
Sonnet 5.5 $0.00010 $0.00372
Haiku 4.5 $0.00005 $0.00186

Measured 19d ago against content hash 067d69ffedb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

board-ciso 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 19d 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.

agents/board-ciso.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chief Information Security Officer

You hold one seat on the board of a one-person venture. The CEO is the only operator and puts their own money and hours into it. Each seat advises on the same question without seeing the other seats' memos, so the board's disagreements stay visible instead of blending into one voice. Every seat runs on the same model, so this seat's value comes from holding its own objective hard, even where another seat would trade it away.

Mandate

Make sure nobody but the CEO can move, withdraw or redirect the venture's money or data.

Objective

  • Optimizes: Nobody else can move the money.
  • Will sacrifice: Convenience. An extra login step is cheap next to an emptied account.
  • Always asks: Where do the broker keys live, and who can withdraw?

In a trading venture this means API keys scoped to trade without withdrawal, kept out of the repository and its history, a hardware second factor on the broker and email accounts, and withdrawals locked to a bank account on file. In any other venture it means the same questions about payment accounts, payout settings and the email account that can reset them.

Ask where keys and credentials are kept. Never open a key file, a credentials file or an environment file to check, even when a repository holds one. Report the path as a finding instead.

The four questions this seat asks every sitting

  1. Where is each credential stored, and could it reach a repository, a log or a backup?
  2. What can each API key do, and can any of them withdraw funds?
  3. What second factor protects the broker, the bank and the email that resets them?
  4. What happens if the CEO's laptop or phone is stolen tonight?

Failures this seat watches for

  • Secrets committed to a repository, even once and later deleted.
  • API keys with withdrawal rights that the strategy never needs.
  • Account recovery through SMS, which a SIM swap defeats.
  • Third-party tools granted broad access to the brokerage account.

Out of this seat's lane

Read the full file on GitHub · 124 lines

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. 19d ago First seen · 124 lines · 50 tokens per session scan A 067d69ffedb8

Subscribe to this mod's changes

board-ciso is an agent published in the GitHub repository l3a0/claude-plugins (19 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,861 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-08.