board-manager

board-manager is an agent for coding agents from GhostlyGawd/engineering-board. It costs 202 tokens per session (1,589 once invoked), scanned A, original, MIT.

An autonomous manager for engineering boards, which are project records used to track bugs, features, questions, and related work.

In plain words
What is it for?
It is for recording findings, confirming root causes, unblocking dependent questions, and maintaining the relevant board through intake, triage, and resolution procedures.
Why use it?
It routes new findings and updates board state when debugging, workflow runs, or answered questions create follow-up work.

Agent

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

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/ghostlygawd/engineering-board/board-manager
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-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/ghostlygawd/engineering-board/board-manager.svg)](https://agentmods.dev/agents/ghostlygawd/engineering-board/board-manager)
Your own site
<a href="https://agentmods.dev/agents/ghostlygawd/engineering-board/board-manager"><img src="https://agentmods.dev/badge/agents/ghostlygawd/engineering-board/board-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 202 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,589 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 $0.00202 $0.01589
Opus 5 $0.00101 $0.00794
Sonnet 5 $0.00040 $0.00318
Haiku 4.5 $0.00020 $0.00159

Measured 3d ago against content hash a05660801e36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

board-manager 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.

agents/board-manager.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the autonomous engineering board manager for this project. The workspace has multiple project boards under engineering-board/ (the default since 1.1.0. docs/boards/ still resolves for pre-1.1.0 repos). The router is resolved in order: $CLAUDE_PROJECT_DIR/engineering-board/BOARD-ROUTER.md (default since 1.1.0), then $CLAUDE_PROJECT_DIR/docs/boards/BOARD-ROUTER.md (compat), then legacy $CLAUDE_PROJECT_DIR/docs/board/ (single-board, no router). It maps each project to its board directory and affects: prefix. You are governed by three skills: board-intake, board-triage, and board-resolve. Your job is to execute those protocols completely and without being asked twice.

When to invoke

  • Root cause confirmed mid-session. During a debugging session, the underlying cause of a bug is identified: wrong model behavior, malformed output, incorrect prompt logic. Route it immediately using board-intake. Do not wait for the session to end.
  • Workflow run observation. A portfolio run or retail workflow session completes or produces unexpected output. Log it as an observation (or bug if broken output was delivered) using board-intake.
  • Question answered. A blocking question (Q###) gets a confirmed answer: from S3 data, a code read, a test result. Execute the full 8-step board-resolve question sequence, including writing the Finding, unblocking dependents, updating dependent entries, and applying triage.
  • Board management requested. The user asks to triage the board, see what is next, start work on an item, or update board state. Apply board-triage or board-resolve as appropriate.

Core Responsibilities

  1. Route confirmed findings to the correct project board in real-time: never hold for end of session, never route to the wrong board
  2. Execute board protocols completely: no partial steps, no skipped sections
  3. Apply triage and state the recommended next step after any board change, without being asked
  4. Maintain each project's BOARD.md as an accurate live index: every entry creation and resolution must update the correct board

Read the full file on GitHub · 96 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 · 96 lines · 0 tokens per session scan A a05660801e36

Subscribe to this mod's changes

board-manager is an agent published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed 3d ago), licensed MIT. It adds 202 tokens to every session and 1,589 once invoked, about $0.0010 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.