agentmods.dev

board-run

board-run is a command for coding agents from GhostlyGawd/engineering-board. It costs 63 tokens per session (1,452 once invoked), scanned A, original, MIT.

A command that drives one project bug or feature through three stages: TDD, review, and validation. TDD means writing tests that describe the desired behavior before implementing it.

In plain words
What is it for?
Use it to take one bug or feature entry through test-driven development, review, and validation until it is resolved, while keeping other session modes unchanged.
Why use it?
It completes one board entry in a single bounded session and avoids the session restarts required when each stage is handled separately.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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

not rated 0 4d ago A scan 63 tokens original MIT
View the source file GhostlyGawd/engineering-board
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-run
Clone the repo
git clone --depth 1 https://github.com/GhostlyGawd/engineering-board

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, 1 plugin.

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-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/ghostlygawd/engineering-board/board-run.svg)](https://agentmods.dev/commands/ghostlygawd/engineering-board/board-run)
Your own site
<a href="https://agentmods.dev/commands/ghostlygawd/engineering-board/board-run"><img src="https://agentmods.dev/badge/commands/ghostlygawd/engineering-board/board-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,452 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 $0.00063 $0.01452
Opus 5 $0.00032 $0.00726
Sonnet 5 $0.00013 $0.00290
Haiku 4.5 $0.00006 $0.00145

Measured 3d ago against content hash 2bf535e706c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

board-run 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.

commands/board-run.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/board-run: drive one entry to resolved, here, now

Advance a single bugs/ or features/ entry through the tdd → review → validate state machine in one session (eb-self B006: the per-discipline worker model needed a session restart per discipline. this command is RFC 0001's inner drive loop as a bounded foreground run). Claim acquire/release is owned by THIS command, exactly as the Stop-hook worker procedure owns it: the discipline subagents never touch locks.

Guard

Read $CLAUDE_PROJECT_DIR/.engineering-board/session-mode.json. This command runs only from a passive session (absent file / null mode):

  • mode == "pm": print Engineering board: currently in PM mode. Start a fresh session to run entries. No action taken. and stop.
  • mode == "worker": print Engineering board: currently in worker mode — the Stop-hook loop is already driving entries. No action taken. and stop.
  • mode == "paused": print Engineering board: currently paused. Run /board-resume first. No action taken. and stop.

This command writes no mode file: it is a bounded foreground run, not a session mode.

Procedure

Step 1: Resolve the entry

  • Validate $1 matches ^[BF][0-9]+$ (bugs and features only: the needs: state machine applies to nothing else). If missing or invalid: print Usage: /board-run <entry-id> (e.g. /board-run B012) — bugs and features only. and stop.
  • Resolve the board via hooks/scripts/board-paths.sh (eb_board_rows). locate the entry file under <board-dir>/bugs/ or <board-dir>/features/ by id: frontmatter. Not found: print Entry <id> not found on any board. Run /board-view to see the board. and stop.
  • Read status: and needs:. If status: resolved: print Entry <id> is already resolved — nothing to run. and stop. If needs: is missing or resolved: print Entry <id> is validated — run /board-resolve <id> to close it. and stop.
  • Determine a session id from .engineering-board/last-stop-stdin.json (session_id), else synthesize one (python3 -c "import uuid; print(uuid.uuid4())").

Read the full file on GitHub · 76 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. 3d ago First seen · 76 lines · 63 tokens per session scan A 2bf535e706c9

Subscribe to this mod's changes

board-run is a command published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,452 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.

Project managementTDDTesting
Related

Other commands, from other repositories

sprint-status

Command "sprint-status" from YuDefine/nuxt-supabase-starter, covering /sprint-status — 開發狀態 dashboard, step 1: branch 概覽, step 2: 未完成工作, 未提交的變更 and 未 push 的 commits.

YuDefine/nuxt-supabase-starter · 11 tokens

backlog

PitWay: Capture out-of-scope work discovered mid-task, without expanding current scope.

thixpin/pitway · 0 tokens

retro

Sprint 回顧 — 分析最近的開發指標.

YuDefine/nuxt-supabase-starter · 13 tokens

execute

Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.

skullninja/coco-workflow · 28 tokens

improve

Build and reconcile a vetted backlog of improvement plans.

howells/arc · 13 tokens

caro-coder-loop

Continuous v1.2.0 feature development — claims next ready beads task, implements via kraken (TDD), opens PR. Loop until no ready work remains.

wildcard/caro · 34 tokens