code-insights CLAUDE.md

Project guidance for Code Insights, a local command-line tool and dashboard that analyses sessions from AI coding tools. It explains the project structure, which is a monorepo—a repository containing several related packages—and its local-only data model.

In plain words
What is it for?
Use it when developing the CLI, React dashboard, or server; working in the pnpm workspace; reading project documentation; or preserving the local SQLite storage and no-cloud data model.
Why use it?
It gives contributors the project context and rules needed to change a live codebase without overlooking its packages, documentation, or privacy requirements.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/melagiri/code-insights/claude-md
Clone the repo
git clone --depth 1 https://github.com/melagiri/code-insights
Per session 2,095 This file is loaded in full into every session.
When invoked 2,095 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 $0.02095 $0.02095
Opus 5 $0.01047 $0.01047
Sonnet 5 $0.00419 $0.00419
Haiku 4.5 $0.00210 $0.00210

Measured 3d ago against content hash d1781ac4fe98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-insights 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 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.

CLAUDE.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Code Insights

Primary Claude Code workspace. All sessions run from this repo root. See docs/ for detailed documentation. This file is the quick reference.


Project Overview

Code Insights is an open-source CLI tool and embedded dashboard for analyzing AI coding sessions. It parses session history from multiple AI coding tools (Claude Code, Cursor, Codex CLI, Copilot CLI, VS Code Copilot Chat), stores structured data in a local SQLite database, and provides both terminal analytics and a browser-based dashboard with LLM-powered insights.

Architecture: Single-repo pnpm workspace monorepo with three packages: CLI, dashboard (Vite + React SPA), and server (Hono API).

Privacy model: Fully local-first. No cloud accounts, no sign-ups, no data leaves the machine. SQLite database at ~/.code-insights/data.db.


Development Philosophy (CRITICAL)

No MVPs, no prototypes, no half-measures. This product is LIVE with real users. Every feature ships as a full, complete implementation. We do not build "minimum viable" anything — we build the real thing, iterate based on feedback, and revert or update if it doesn't work out.

This principle applies to planning, designing, AND implementation:

  • Planning: Don't scope down to "MVP facet set" vs "ideal set." Design the complete solution.
  • Designing: Don't propose phased rollouts with "ship phase 1, add phase 2 later." Design it right the first time.
  • Implementing: Don't cut corners with "we can add this later." Build it now or explicitly decide not to build it.

Configuration Hierarchy

Priority Source Scope
1 (Highest) This project CLAUDE.md Code Insights workflows, ceremony, agents
2 Session Mode Educational context, learning mode
3 Global ~/.claude/CLAUDE.md General best practices

Key overrides from global config:

Behavior Global Default Code Insights Override
Planning Ask first Sub-agents autonomous in their domain
File Creation Ask first Agents create files autonomously in their domain
Review Process Single reviewer Triple-layer (TA Insider + Outsider + Synthesis)
PR Merges Normal BLOCKED — only founder merges

Read the full file on GitHub · 171 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. 3d ago First seen · 171 lines · 2,095 tokens per session scan A d1781ac4fe98

Subscribe to this mod's changes

code-insights CLAUDE.md is an instructions file published in the GitHub repository melagiri/code-insights (76 stars, last pushed 3mo ago), licensed MIT. It adds 2,095 tokens to every session, about $0.0105 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 2026-08-30.