board-install-permissions

board-install-permissions is a command for Claude Code from GhostlyGawd/engineering-board. It costs 54 tokens per session (948 once invoked), scanned B, original, MIT.

An interactive command that prepares the engineering-board plugin's permission list for Claude settings. It displays the requested permissions and prints commands for you to run.

In plain words
What is it for?
Use it when setting up the plugin or checking whether its required permissions are already installed.
Why use it?
It avoids repeatedly approving the plugin's board-related commands while keeping installation under your control.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; names the SlashCommand tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the engineering-board plugin — 6 skills, 21 commands, 8 agents, 4 hooks, 1 MCP server shipped together

Good fit Use it when setting up the plugin or checking whether its required permissions are already installed.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add GhostlyGawd/engineering-board
Claude Code
/plugin install engineering-board

Made for: Claude Code.

Or install engineering-board, the plugin that ships this one along with the rest of its 6 skills, 21 commands, 8 agents, 4 hooks, 1 MCP server.

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-install-permissions

README.md
[![agentmods](https://agentmods.dev/badge/commands/ghostlygawd/engineering-board/board-install-permissions.svg)](https://agentmods.dev/commands/ghostlygawd/engineering-board/board-install-permissions)
Your own site
<a href="https://agentmods.dev/commands/ghostlygawd/engineering-board/board-install-permissions"><img src="https://agentmods.dev/badge/commands/ghostlygawd/engineering-board/board-install-permissions.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 948 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00054 $0.00948
Opus 5 $0.00027 $0.00474
Sonnet 5 $0.00011 $0.00190
Haiku 4.5 $0.00005 $0.00095

Measured 6d ago against content hash f277172043ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

board-install-permissions scanned grade B with 1 finding 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add the engineering-board permission patterns to your `~/.claude/settings.json` so the plugin can run its claim scripts and slash commands without prompting each time. This command is interactive-only: it prints the exac
commands/board-install-permissions.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/board-install-permissions: install plugin allowlist

Add the engineering-board permission patterns to your ~/.claude/settings.json so the plugin can run its claim scripts and slash commands without prompting each time. This command is interactive-only: it prints the exact claude config add lines for you to run yourself.

What to do

Step 0: Fast-path: check if already installed

Run:

bash $CLAUDE_PLUGIN_ROOT/hooks/scripts/board-permission-self-check.sh

If the script exits 0 (all installed), print:

All engineering-board permissions installed. Nothing to do.

Then stop.

If the script exits 2 (manifest unreadable), print:

ERROR: could not read required-permissions.json. Check that CLAUDE_PLUGIN_ROOT is set correctly.

Then stop.

Step 1: Read and display the proposed allowlist

Read ${CLAUDE_PLUGIN_ROOT}/references/required-permissions.json. Parse the patterns array.

Print exactly:

engineering-board requests the following permissions for your ~/.claude/settings.json:

Then print a numbered list. For each pattern entry, print two lines:

  N. <tool>: <pattern>
     Reason: <rationale>

Example:

  1. Bash: bash $CLAUDE_PLUGIN_ROOT/hooks/scripts/board-scratch-append.sh:*
     Reason: passive capture: every Stop turn appends the extractor's findings to the scratch session file
  2. SlashCommand: /pm-start
     Reason: Start PM (consolidator) session for engineering board

(Use ASCII -- not em-dash. the rationale field is copied verbatim from the JSON.)

Step 2: Confirmation prompt

Print exactly:

Add these to your user-scope settings? Reply YES (uppercase) to confirm, or anything else to cancel.

Then stop and wait for the user's reply.

Step 3: Handle user reply

If the user replied YES (exact uppercase match):

Print exactly:

Run the following commands to add each permission. Copy and paste them into your terminal:

Then print one line per pattern:

claude config add permissions.allow "<tool>(<pattern>)"

Read the full file on GitHub · 121 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. 6d ago First seen · 121 lines · 54 tokens per session scan B f277172043ec

Subscribe to this mod's changes

board-install-permissions is a command published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed 7d ago), licensed MIT. It adds 54 tokens to every session and 948 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.