board-setup

A setup command that prepares an engineering board, checks whether its permissions are ready, and prints a short status summary. It can also run an optional pattern-intelligence demonstration.

In plain words
What is it for?
Use it after installation to create or detect a project's board, verify its setup, and leave the session ready for passive capture.
Why use it?
It combines the normal initialization and readiness checks into one repeatable step, while avoiding re-creating a board that already exists.

Command

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 commands/ghostlygawd/engineering-board/board-setup
Clone the repo
git clone --depth 1 https://github.com/GhostlyGawd/engineering-board
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 722 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 $0.00054 $0.00722
Opus 5 $0.00027 $0.00361
Sonnet 5 $0.00011 $0.00144
Haiku 4.5 $0.00005 $0.00072

Measured yesterday against content hash 3722298e9021, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

board-setup 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 yesterday.

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.

commands/board-setup.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/board-setup: one command from install to a working board

Collapse the install to value path (previously: /board-init + /board-install-permissions + mode-learning) into one idempotent step (eb-self F002). This command composes existing pieces: it introduces no new state.

What to do

Step 1: Infer the project name

Use $1 if given. Otherwise default to the basename of $CLAUDE_PROJECT_DIR, lowercased with any character outside [a-z0-9-] replaced by -. If the sanitized name is empty, ask the user for a project name and stop.

Step 2: Scaffold (or detect an existing board)

Check whether the resolver already finds a board for this project (source hooks/scripts/board-paths.sh. if engineering-board/BOARD-ROUTER.md lists the project, the board exists).

  • Board exists: skip scaffolding: say so in the Step 4 summary ("board already set up"). Never re-scaffold or clobber.
  • No board: execute the /board-init procedure (Read commands/board-init.md and follow its Steps 1-7) with the inferred project name and default affects-prefix. Keep its .gitignore guidance print-only, as that command specifies.

Step 3: Permission self-check (print the paste block only if needed)

Run:

bash "$CLAUDE_PLUGIN_ROOT/hooks/scripts/board-permission-self-check.sh"
  • Exit 0 (all installed): note "pipeline permissions: installed" for the summary.
  • Exit 1 (some missing): print the missing-rule paste block exactly as /board-install-permissions would (the self-check output lists the missing patterns), preceded by one line: To let the pipeline run without prompts, paste the block below into a terminal (interactive by design — this command never edits your settings). Note "pipeline permissions: N missing (paste block above)" for the summary.

Do NOT edit any settings file yourself: permission installation is interactive by design.

Step 4: Report (three readiness lines + one optional first-win line)

Print:

Board ready: engineering-board/<project>/ (<scaffolded fresh | already set up>).
Capture is on: findings land in _sessions/ automatically — run /board-promote <project> to preview them, or /pm-start for advanced batch mode.
Pipeline permissions: <installed | N missing — paste block above>.
Try the pattern-intelligence sample: /board-demo

Read the full file on GitHub · 55 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. yesterday First seen · 55 lines · 54 tokens per session scan A 3722298e9021

Subscribe to this mod's changes

board-setup is a command published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 722 once invoked, about $0.0003 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.