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.
/plugin marketplace add mingrath/wfdashnpx agentmods add plugins/mingrath/wfdash/wayfinder-toolsgit clone --depth 1 https://github.com/mingrath/wfdashGrade A, and why
wayfinder-tools 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 2d 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.
What it actually says
{
"name": "wayfinder-tools",
"version": "0.1.5",
"description": "A local, read-only browser dashboard over your wayfinder maps — plus the charting rules, injected into every /wayfinder session.",
"author": {
"name": "Mingrath Mekavichai",
"url": "https://github.com/mingrath"
},
"homepage": "https://github.com/mingrath/wfdash",
"repository": "https://github.com/mingrath/wfdash",
"license": "MIT",
"keywords": [
"wayfinder",
"github-issues",
"dashboard",
"planning"
]
}
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.
- 2d ago First seen · 19 lines scan A 7a098932ad2d
wayfinder-tools is a plugin published in the GitHub repository mingrath/wfdash (14 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
ai-team-os
AI Agent Team Operating System for Claude Code with 113 MCP tools (incl. 42 ecosystem research tools), 25 agent templates, 11 hooks / 15 lifecycle events. Persistent team management, structured meetings, task wall, real-time React dashboard, and Ecosystem Research Platform v2 (progressive 4-stage deep-review funnel…
fleetdeck
Localhost fleet board for Claude Code, guarded by a release-bound compatibility policy.
thoth
Dashboard-centric Agent Project OS for auditable AI execution, persistent project state, and human-visible workflow orchestration.
promptline
Local, read-only visual timeline of your Claude Code prompt history - dashboard, activity heatmap, and searchable per-project/session feed. Binds to 127.0.0.1 only, no outbound network calls, nothing written back to /.claude.
claude-telemetry
Per-turn knowledge-base hit-rate telemetry + offline dashboard for Claude Code. Collects hook events into project-local .claude/telemetry and renders a self-contained HTML dashboard.
clawenable
Produces, reviews, and improves standalone single-file HTML artifacts using vanilla HTML, inline CSS, and vanilla JS — no frameworks or CDN. Use for: comparison matrices, interactive dashboards, timeline roadmaps, review surfaces, visual explainers.