logs-locally-plugin: Instructions file for Claude Code

CLAUDE.md

logs-locally-plugin CLAUDE.md is an instructions file for Claude Code from Laotree/logs-locally-plugin. It costs 1,485 tokens per session, scanned A, original, MIT.

A Rust program that reads Claude Code session files in JSONL format and stores them in a local SQLite database. JSONL is a text format with one JSON record per line, and SQLite is a database kept in a file.

In plain words
What is it for?
Use it to continuously scan Claude session folders, parse and deduplicate sessions, watch for changed files, and query the resulting SQLite database.
Why use it?
It turns scattered session logs into searchable local records and avoids importing the same session again after a restart. It can also remove records older than a configured age.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is Laotree/logs-locally-plugin's own configuration. It tells Claude Code how to work on logs-locally-plugin 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 logs-locally-plugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Laotree/logs-locally-plugin. 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/Laotree/logs-locally-plugin/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Laotree/logs-locally-plugin

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 logs-locally-plugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/laotree/logs-locally-plugin/claude-md.svg)](https://agentmods.dev/instructions/laotree/logs-locally-plugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/laotree/logs-locally-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/laotree/logs-locally-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,485 This file is loaded in full into every session.
When invoked 1,485 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01485 $0.01485
Opus 5 $0.00743 $0.00743
Sonnet 5 $0.00297 $0.00297
Haiku 4.5 $0.00148 $0.00148

Measured 6d ago against content hash 3cfa0c08ca4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

logs-locally-plugin 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 6d 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 · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

logs-locally-plugin — Claude session JSONL → Local SQLite storage

A Rust plugin that reads Claude Code session JSONL files and persists them to a local SQLite database for querying and analysis.

Build & Run

cargo build --release
cargo run --release       # reads config.json from cwd

Config

See config.json. Key fields:

  • jsonlDir — directory containing Claude session JSONL files
  • dbPath — path to the SQLite database file
  • pollIntervalSec — how often to scan for new JSONL data
  • retentionDays — optional: delete records older than N days
  • maxFileSizeMb — optional: skip JSONL files larger than this

Architecture

main.rs         — event loop: scan JSONL dir → parse sessions → upsert to SQLite
config.rs       — config.json loading and normalization
db.rs           — SQLite schema, upsert, query, and cleanup logic
parser.rs       — JSONL parsing, session extraction, dedup by session ID
watcher.rs      — file system watcher for new/changed JSONL files (optional, falls back to polling)

state.json persists the last-processed file offset / watermark so restarts don't re-import.

Key Behaviors

  • Reads all .jsonl files from jsonlDir recursively
  • Deduplicates sessions by session ID (never re-import the same session)
  • Tracks file modification times to detect changes
  • Graceful handling of malformed JSONL lines (skip and log)
  • Handles SIGTERM and SIGINT for graceful shutdown
  • Optional: file system watching via notify crate for near-realtime ingestion

Database Schema (SQLite)

CREATE TABLE IF NOT EXISTS sessions (
    id TEXT PRIMARY KEY,          -- Claude session ID
    title TEXT,
    model TEXT,                   -- model used (e.g. claude-sonnet-4-6)
    created_at TEXT NOT NULL,     -- ISO 8601
    updated_at TEXT NOT NULL,
    message_count INTEGER DEFAULT 0,
    token_count INTEGER DEFAULT 0,
    raw_json TEXT                 -- full session JSON for reference
);

CREATE TABLE IF NOT EXISTS messages (
    id TEXT PRIMARY KEY,
    session_id TEXT NOT NULL REFERENCES sessions(id),
    role TEXT NOT NULL,           -- "user" | "assistant"
    content TEXT NOT NULL,
    created_at TEXT NOT NULL,
    token_count INTEGER DEFAULT 0,
    parent_id TEXT REFERENCES messages(id)
);

CREATE INDEX IF NOT EXISTS idx_messages_session ON messages(session_id);
CREATE INDEX IF NOT EXISTS idx_messages_created ON messages(created_at);

Read the full file on GitHub · 196 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. 6d ago First seen · 196 lines · 1,485 tokens per session scan A 3cfa0c08ca4a

Subscribe to this mod's changes

logs-locally-plugin CLAUDE.md is an instructions file published in the GitHub repository Laotree/logs-locally-plugin (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,485 tokens to every session, about $0.0074 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.

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 · 5,182 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

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

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