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 commands/ghostlygawd/engineering-board/board-viewgit 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/commands/ghostlygawd/engineering-board/board-view)<a href="https://agentmods.dev/commands/ghostlygawd/engineering-board/board-view"><img src="https://agentmods.dev/badge/commands/ghostlygawd/engineering-board/board-view.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 | $0.00033 | $0.00809 |
| Opus 5 | $0.00016 | $0.00404 |
| Sonnet 5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
board-view 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/board-view: render the board as HTML
Generate a browsable Kanban view of the board for project: ${1:-all resolved projects}
What to do
Run the deterministic generator (it resolves the board location via the shared resolver and reuses the same brand tokens as the landing page):
bash "$CLAUDE_PLUGIN_ROOT/hooks/scripts/board-view.sh" ${1:-} $([ "$ARGUMENTS" != "${ARGUMENTS/--stdout/}" ] && echo --stdout)
- With no arguments it renders every project the router resolves.
- With a project name it renders just that board.
--stdoutprints the HTML instead of writingboard.html.--link-base <url>prefixes entry-card links with an absolute base (e.g. a GitHub blob URL) so a hosted copy ofboard.htmlclicks through to the entry sources. without it, links are relative (they resolve locally and in the GitHub file view). Also settable via theEB_VIEW_LINK_BASEenv var.--stampappends a "Generated from<git short-sha>" line to the footer - opt-in because it deliberately breaks the default byte-determinism.--demo-dir <run-dir>is an internal/board-demointegration surface. It reads that run'sgraph.jsonand proposed hypothesis Markdown, writespattern-intelligence.html, and never opens a browser. Normal users should invoke/board-demo, which validates and reports the contained run.
The script writes engineering-board/<project>/board.html: a single
self-contained file (all CSS inlined, no network, no JavaScript required). It
is byte-deterministic (stable sort by entry id, no embedded timestamp), so it
can be committed alongside BOARD.md without spurious diffs, and it renders
directly on GitHub or in any browser.
What it shows
- A read-only pattern-intelligence section with ranked cluster scores and components, linked canonical members, H### state, stale bindings, cited evidence, alternatives, and falsifiers. Scores prioritize investigation. they are not causal confidence.
- A four-column Kanban of bugs/features across the pipeline: To do
(
needs: tdd) to Review (needs: review) to Validate (needs: validate) to Done (status: resolved). Cards show id, priority, title,affects,patterntags, and ablockedbadge when applicable. - Separate lanes for Questions and Observations, and for durable Learnings.
- Light/dark theme (follows the viewer's
prefers-color-scheme).
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 · 69 lines · 0 tokens per session scan A d5576df1da67
board-view is a command published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 809 once invoked, about $0.0002 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 commands, from other repositories
project-recap
Generate a visual project recap for context switching.
os-meeting
快速创建和管理AI团队会议.
workspace
Testany Workspace, 管理工作空间,成员权限,团队组织.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).
triage-issues
Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.