local-agent-viewer: Instructions file for Claude Code

CLAUDE.md

local-agent-viewer CLAUDE.md is an instructions file for Claude Code, Codex from maxturazzini/local-agent-viewer. It costs 6,059 tokens per session, scanned B, original, MIT.

Instructions for LocalAgentViewer, a local long-term memory tool for AI-agent conversations. It imports conversation logs and exports into one SQLite database, then provides a web dashboard, classification, and optional vector search.

In plain words
What is it for?
Use it to parse Claude Code, Codex CLI, Claude Desktop, ChatGPT, or Claude.ai histories; search them; manage a knowledge base; and run the local dashboard.
Why use it?
It gathers histories from different agent and chat tools so they can be searched and reviewed in one place instead of remaining in separate log formats.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is maxturazzini/local-agent-viewer's own configuration. It tells Claude Code and Codex how to work on local-agent-viewer 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 local-agent-viewer configures →

Reuse

Borrowing it

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

Made for: Claude Code, Codex.

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 local-agent-viewer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maxturazzini/local-agent-viewer/claude-md.svg)](https://agentmods.dev/instructions/maxturazzini/local-agent-viewer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/maxturazzini/local-agent-viewer/claude-md"><img src="https://agentmods.dev/badge/instructions/maxturazzini/local-agent-viewer/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,059 This file is loaded in full into every session.
When invoked 6,059 The same file — it is already loaded in full.
Security scan B 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 $0.06059 $0.06059
Opus 5 $0.03030 $0.03030
Sonnet 5 $0.01212 $0.01212
Haiku 4.5 $0.00606 $0.00606

Measured today against content hash 02cc63512161, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

local-agent-viewer CLAUDE.md scanned grade B 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 today.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **`bash_commands` IS all Bash** (LAV-80 — the old "24,8% only, never call it the Bash error rate" caveat is RETIRED): the `is_file_related_bash` gate is gone, any non-empty command is stored (+47.316 rows, 3,05x). True
CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 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.

What this is

LocalAgentViewer (LAV) — local long-term memory for AI agent interactions. Parses JSONL/JSON logs from Claude Code, Codex CLI, Claude Desktop, ChatGPT, and Anthropic claude.ai account exports into a single SQLite database with a web dashboard, AI classification, and optional vector search.

Commands

# Install (zero dependencies for core, extras for optional features)
pip install -e .              # core only
pip install -e ".[all]"       # everything (qdrant, openai, fastmcp)

# Parse & serve
lav-parse                     # incremental parse from local JSONL
lav-parse --project myProject # parse one project
lav-parse --full              # full reparse
lav-parse --since 2026-06-01  # bounded re-read (additive, insert-only; excl. --full)
lav-parse-chatgpt             # parse ChatGPT export
lav-parse-claude-ai           # parse Anthropic claude.ai export folder (data-*-batch-0000)
lav-server                    # start server on :8764

# Unified CLI — query & KB management (zero extra deps)
lav search "query"            # FTS5 full-text search
lav search "query" --project miniMe --limit 5 --format brief
lav show <session_id>         # full interaction transcript
lav kb search "semantic query" # Qdrant vector search
lav kb status <session_id>    # check if indexed
lav kb index <session_id> --tags "tag1,tag2"
lav kb remove <session_id>
lav kb tags <session_id> --set "new,tags"
lav sync                      # trigger sync (needs LAV_API_KEY)
lav sync --scope project --project miniMe
lav pricing list              # list active pricing
lav pricing add --model X --input 5.0 --output 25.0 --from-date 2026-01-01
lav backfill tool-outcomes    # stamp tool_call_id + outcome on historical tool rows
lav backfill tool-kind        # re-derive mcp_tool_calls.kind (--reclassify after a whitelist edit)
lav backfill claude-ai-outcomes  # recover claude.ai is_error from markers in messages (LAV-83)
lav backfill codex-titles     # rebuild Codex display/summary from state_<N>.sqlite (LAV-91)
lav backfill codex-titles --state-db /tmp/agent_state_5.sqlite  # apply another node's titles

# Specialized CLIs (still available)
lav-classify                  # AI classification (needs OPENAI_API_KEY)
lav-index                     # Qdrant vector indexing
lav-mcp                       # MCP server (needs fastmcp)
lav-pricing list              # list model pricing (standalone)
lav-pricing add --model X ... # add/update pricing entry
lav-pricing seed              # insert default pricing data

Read the full file on GitHub · 183 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. today Changed · +4 lines · +656 tokens per session 02cc63512161
  2. 8d ago First seen · 179 lines · 5,403 tokens per session scan B 381bd09dee46

Subscribe to this mod's changes

local-agent-viewer CLAUDE.md is an instructions file published in the GitHub repository maxturazzini/local-agent-viewer (13 stars, last pushed yesterday), licensed MIT. It adds 6,059 tokens to every session, about $0.0303 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens