agentmods.dev

noctrace: Instructions file for Claude Code

CLAUDE.md

noctrace CLAUDE.md is an instructions file for Claude Code from nyktora/noctrace. It costs 3,561 tokens per session, scanned A, original, MIT.

Repository instructions for noctrace, a local browser-based timeline that shows AI coding-agent sessions as a Chrome DevTools-style network waterfall.

In plain words
What is it for?
Working on noctrace's log parsing and waterfall display, including agent groups, tool-call timing, nested sub-agents, and token calculations.
Why use it?
They explain where Claude Code, Codex CLI, and GitHub Copilot Chat store their session logs and how the visualizer reads them.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions subagents.

This is nyktora/noctrace's own configuration. It tells Claude Code how to work on noctrace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything noctrace configures →

not rated 5repo 6mo ago A scan 3,561 tokens original MIT
View source ↗ nyktora/noctrace
Reuse

Borrowing it

Nothing to install: this file belongs to nyktora/noctrace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nyktora/noctrace/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nyktora/noctrace

Made for: Claude Code.

Wrote 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.

agentmods badge for noctrace CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nyktora/noctrace/claude-md/github.svg)](https://agentmods.dev/instructions/nyktora/noctrace/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nyktora/noctrace/claude-md"><img src="https://agentmods.dev/badge/instructions/nyktora/noctrace/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for noctrace CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nyktora/noctrace/claude-md"><img src="https://agentmods.dev/badge/instructions/nyktora/noctrace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,561 This file is loaded in full into every session.
When invoked 3,561 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03561 $0.03561
Opus 5.5 $0.01424 $0.01424
Sonnet 5.5 $0.00712 $0.00712
Haiku 4.5 $0.00356 $0.00356

Measured 2mo ago against content hash fb413c851fe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

noctrace CLAUDE.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

51. ✅ Docker support (`npx noctrace --docker <container>`: inject-and-stream watcher, auto-detects claude config dir, host URL resolution, curl/wget fallback)
CLAUDE.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Noctrace

Chrome DevTools Network-tab-style real-time waterfall visualizer for AI coding agent workflows (Claude Code, Codex CLI, GitHub Copilot Chat). Open source, local-only, zero config.

Project Overview

Noctrace passively reads session logs from Claude Code (~/.claude/projects/), Codex CLI (~/.codex/sessions/), and GitHub Copilot Chat (VS Code workspaceStorage) and renders them as an interactive waterfall timeline in a browser tab. Agents appear as collapsible row groups, tool calls as nested rows with colored timing bars on a shared time axis.

JSONL Log Paths

Claude Code:

  • Main session: ~/.claude/projects/<project-slug>/<session-id>.jsonl
  • Sub-agent sessions: ~/.claude/projects/<project-slug>/<session-id>/subagents/agent-<agent-id>.jsonl

Main and sub-agent logs are parsed by separate functions (parseSessionContent and parseSubAgentContent). Sub-agent rows are attached as children of their parent agent row in the API route, after both are independently parsed. Any per-row computation (like token deltas) must be done in both parsers.

Codex CLI:

  • Sessions: ~/.codex/sessions/YYYY/MM/DD/rollout-*.jsonl (override with CODEX_HOME)

GitHub Copilot Chat:

  • Sessions: VS Code workspaceStorage/*/GitHub.copilot-chat/ JSON session files

Tech Stack

  • Runtime: Node.js 20 LTS
  • Server: Express 5.x + ws 8.x (WebSocket)
  • File watching: chokidar 4.x
  • Client: React 19 + Vite 8 + Tailwind CSS 4
  • State: Zustand 5.x
  • No database — JSONL files on disk are the source of truth

Commands

  • npm run dev — starts server + Vite dev server concurrently
  • npm run build — builds client, bundles server
  • npm test — runs Vitest test suite
  • npm run lint — runs ESLint
  • npm run typecheck — runs TypeScript compiler in check mode
  • npm run test:smoke — builds and runs production smoke tests (verifies npx noctrace works)

Code Style

  • TypeScript strict mode everywhere (server and client)
  • ES modules only (import/export), never CommonJS
  • Functional React components with hooks, no class components
  • Name files with kebab-case: waterfall-row.tsx, jsonl-parser.ts
  • All SVG icons are inline React components in src/client/icons/ — never use emojis

Read the full file on GitHub · 228 lines

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. 2mo ago First seen · 228 lines · 3,561 tokens per session scan A fb413c851fe5

Subscribe to this mod's changes

noctrace CLAUDE.md is an instructions file published in the GitHub repository nyktora/noctrace (5 stars, last pushed 6mo ago), licensed MIT. It adds 3,561 tokens to every session, about $0.0142 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Codeai-agentsanthropicclaudedevtoolsobservability
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens