Dashboard Dev

A role guide for developing a React and Vite dashboard, including a knowledge graph—a visual map of connected information—and memory browsing. It defines the project’s required graph library, styling rules, and interaction behavior.

In plain words
What is it for?
Building or modifying graph pages, memory search and browsing, entity exploration, custom graph drawing, dragging, and hover or click behavior.
Why use it?
It prevents changes that would break the dashboard’s graph rendering or interactions. It also tells the agent when to discuss performance before adding new visualizations.

Agent for Claude Code

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/shawnhack/exocortex/dashboard-dev
Clone the repo
git clone --depth 1 https://github.com/shawnhack/exocortex

Made for: Claude Code.

Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 255 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 $0.00002 $0.00255
Opus 5 $0.00001 $0.00128
Sonnet 5 $0.00000 $0.00051
Haiku 4.5 $0.00000 $0.00026

Measured yesterday against content hash 44e297a0c4ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Dashboard Dev 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.

.claude/agents/dashboard-dev.md · 29 lines

What it actually says

Dashboard Dev

Core Responsibilities

  • React + Vite dashboard application
  • Knowledge graph visualization (force-graph)
  • Neural Interface theme (black/cyan terminal aesthetic)
  • Memory browsing, search, and entity exploration

Key Files

  • packages/dashboard/src/ — React application
  • packages/dashboard/src/pages/Graph.tsx — knowledge graph page

Coding Constraints

  • Use force-graph (2D canvas), NOT 3d-force-graph (was tried, switched back)
  • CSS vars from index.css (--bg-root, --cyan, --text-*)
  • Manual pointer detection — force-graph built-in nodePointerAreaPaint/onNodeHover/onNodeClick is broken with custom nodeCanvasObject
  • Manual drag via mousedown capture phase → set node.fx/fy → mousemove → mouseup
  • Use cooldownTicks(Infinity) — if simulation cools, render loop stops and all interaction breaks
  • Never call graph.graphData(gd) to update visuals — restarts force simulation. Use d3ReheatSimulation()
  • Single useEffect with initedRef guard for initialization

Escalation

  • New visualization types: discuss performance implications
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 · 29 lines · 2 tokens per session scan A 44e297a0c4ec

Subscribe to this mod's changes

Dashboard Dev is an agent published in the GitHub repository shawnhack/exocortex (1 stars, last pushed 27d ago), licensed MIT. It adds 2 tokens to every session and 255 once invoked, about $0.0000 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.

Related

Other agents, from other repositories

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens