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 nyktora/noctracenpx agentmods add plugins/nyktora/noctrace/noctracegit clone --depth 1 https://github.com/nyktora/noctraceWrote 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/plugins/nyktora/noctrace/noctrace)<a href="https://agentmods.dev/plugins/nyktora/noctrace/noctrace"><img src="https://agentmods.dev/badge/plugins/nyktora/noctrace/noctrace.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
noctrace 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.
What it actually says
{
"name": "noctrace",
"version": "1.6.0",
"description": "Chrome DevTools Network-tab-style waterfall visualizer for AI coding agent workflows — supports Claude Code, Codex CLI, and GitHub Copilot Chat",
"author": "Nyktora Group LLC",
"license": "MIT",
"homepage": "https://nyktora.github.io/noctrace/",
"repository": "https://github.com/nyktora/noctrace",
"keywords": ["devtools", "waterfall", "observability", "timeline", "context-health", "claude-code", "agent-monitoring", "ai-observability"],
"category": "observability",
"minClaudeCodeVersion": "1.0.0",
"capabilities": ["hooks", "mcp"]
}
What it installs
The manifest is a name and a version. 5 skills, 4 agents, 1 MCP server travel with it, and installing the plugin installs all of them — 422 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill auto-scan A 124 tokens
- Skill context-health A 37 tokens
- Skill waterfall-ui A 34 tokens
- Skill jsonl-parser A 32 tokens
- Skill server-setup A 32 tokens
- Agent qa-reviewer A 30 tokens
- Agent ui-engineer A 45 tokens
- Agent parser-engineer A 43 tokens
- Agent server-engineer A 45 tokens
- MCP server noctrace A not measured
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 · 14 lines scan A 094ee9d32f54
noctrace is a plugin published in the GitHub repository nyktora/noctrace (5 stars, last pushed 4mo 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 2026-08-31.
Other plugins, from other repositories
sandy-cli
Sandy: sandboxed TypeScript execution for AWS queries via the sandy CLI.
webview-devtools-mcp
DevTools for any WebView — no remote-debugging port required. Works in Safari/iOS WebView/Lark Web App and more.
cchad
Detect a repo's stack and configure Claude Code (MCP servers + skills), recorded in a committed manifest.
neural-memory
A knowledge graph that maps your codebase into layered, navigable neural nodes — understand any function without reading the entire file.
e2e-alertmanager-test
Render end-to-end alert notification previews (email/Slack/JSON) through a live Alertmanager.
banyandb-bydbql
Generate, validate, and execute read-only BanyanDB BydbQL for SkyWalking data.