agentmods.dev

agent-chatlens: Instructions file for Claude Code

CLAUDE.md

agent-chatlens CLAUDE.md is an instructions file for Claude Code from kangjinghang/agent-chatlens. It costs 1,281 tokens per session, scanned A, original, MIT.

Project instructions for Agent ChatLens, a browser-based React app that displays AI coding-assistant session files from tools such as Claude Code, OpenClaw, and Gemini CLI.

In plain words
What is it for?
Use it when changing session-format detection, parsing messages and actions, the React interface, builds, or tests.
Why use it?
It documents the supported file formats, development commands, test setup, and the parts of the app responsible for reading sessions.

Instructions file for Claude Code

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

This is kangjinghang/agent-chatlens's own configuration. It tells Claude Code how to work on agent-chatlens 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 agent-chatlens configures →

not rated 5repo 3mo ago A scan 1,281 tokens original MIT
View source ↗ kangjinghang/agent-chatlens kangjinghang.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to kangjinghang/agent-chatlens. 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/kangjinghang/agent-chatlens/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kangjinghang/agent-chatlens

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 agent-chatlens CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kangjinghang/agent-chatlens/claude-md/github.svg)](https://agentmods.dev/instructions/kangjinghang/agent-chatlens/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kangjinghang/agent-chatlens/claude-md"><img src="https://agentmods.dev/badge/instructions/kangjinghang/agent-chatlens/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 agent-chatlens CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kangjinghang/agent-chatlens/claude-md"><img src="https://agentmods.dev/badge/instructions/kangjinghang/agent-chatlens/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,281 This file is loaded in full into every session.
When invoked 1,281 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01281 $0.01281
Opus 5 $0.00641 $0.00641
Sonnet 5 $0.00256 $0.00256
Haiku 4.5 $0.00128 $0.00128

Measured 9d ago against content hash 60703262cf5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-chatlens CLAUDE.md 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 9d 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.

CLAUDE.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Agent ChatLens is a pure-frontend React app for viewing AI agent session files (JSONL/JSON format). It supports OpenClaw, Claude Code, and Gemini CLI session formats with auto-detection.

Commands

  • Dev server: bun dev (runs on port 3000, auto-opens browser)
  • Build: bun run build (runs tsc && vite build, outputs to dist/)
  • Preview production build: bun run preview
  • Type checking: npx tsc --noEmit
  • Run tests: bun test (Vitest, runs all src/**/*.test.ts)
  • Run a single test: bun test src/parser/__tests__/parser.test.ts
  • Watch tests: bun run test:watch

No linter or formatter is configured.

Testing

Tests use Vitest and focus on the parser layer (src/parser/__tests__/). Synthetic fixtures cover format detection, chunk merging, tool calls/results, and edge cases. Real session files from ~/.openclaw/ and ~/.claude/ are also tested when present. Note: tsconfig.json excludes test files from type checking — only npx tsc --noEmit for src/ (non-test) code.

Architecture

Session file (.jsonl/.json) → parseSession() → ParsedSession → groupIntoTurns() → Turn[] → SessionList → TurnView / TimelineView → ContentBlock renderers

Parser layer (src/parser/)

The core of the app. Three format-specific parsers produce a unified DisplayMessage[]:

  • types.ts — Shared types: DisplayMessage, ContentBlock (text/thinking/toolUse/toolResult), ParsedSession, Turn, RawEntry
  • index.ts — parseSession() entry point: tries JSON parse first (Gemini CLI), then falls back to JSONL line parsing. Auto-detects format via detectFormat(), delegates to the correct parser. Also exports groupIntoTurns() for turn-based grouping.
  • openclaw.ts — Parses OpenClaw format: all entries have type="message", role inside message.role, tool calls use type="toolCall" with arguments
  • claude-code.ts — Parses Claude Code format: entry types are "user"/"assistant", assistant messages are streamed (multiple chunks sharing same message.id that get merged via mergeAssistantChunks()), IDs use uuid/parentUuid
  • gemini-cli.ts — Parses Gemini CLI format: single JSON file with messages array, parts contain text/functionCall/functionResponse

Read the full file on GitHub · 70 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. 9d ago First seen · 70 lines · 1,281 tokens per session scan A 60703262cf5e

Subscribe to this mod's changes

agent-chatlens CLAUDE.md is an instructions file published in the GitHub repository kangjinghang/agent-chatlens (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,281 tokens to every session, about $0.0064 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.

Claude Codeagent-debuggingai-agentclaudeconversation-analysisjsonl-viewer
Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens