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.
npx agentmods add agents/ghostlygawd/engineering-board/board-managergit clone --depth 1 https://github.com/GhostlyGawd/engineering-boardWrote 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.
[](https://agentmods.dev/agents/ghostlygawd/engineering-board/board-manager)<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>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.
| Model | Per session | Once 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 |
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.
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
- Route confirmed findings to the correct project board in real-time: never hold for end of session, never route to the wrong board
- Execute board protocols completely: no partial steps, no skipped sections
- Apply triage and state the recommended next step after any board change, without being asked
- Maintain each project's BOARD.md as an accurate live index: every entry creation and resolution must update the correct board
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.
- 3d ago First seen · 96 lines · 0 tokens per session scan A a05660801e36
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.
Other agents, from other repositories
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
Orchestrator
Task coordination and agent delegation.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
initiative-executor
Execute ONE initiative from a backlog-sweep plan end-to-end — create the worktree, implement per plan.md, validate, open the PR, return a >> envelope. Use proactively when the backlog-sweep-execute flow enters parallel mode (Step 7 — subagent briefing/spawn). Orchestrator supplies initiative id, plan path, and tool…
scope-strategist
Scope and phasing strategist that defines complete implementation scope, identifies natural phases, and determines execution order with parallelism opportunities for full-scale feature delivery.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.