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.
npx agentmods add instructions/melagiri/code-insights/claude-mdgit clone --depth 1 https://github.com/melagiri/code-insightsWhat 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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 3d ago First seen · 171 lines · 2,095 tokens per session scan A d1781ac4fe98
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.
Other instructions, from other repositories
pad CLAUDE.md
Instructions for PerpetualSoftware/pad, covering pad — development guide, what this is, architecture, build & install and quick iteration loop.
sverklo CLAUDE.md
Instructions for sverklo/sverklo, covering sverklo development, using sverklo tools, project structure and build & test.
brain-os AGENTS.md
Instructions for brainOS-HQ/brain-os, covering agents.md, context, the hard rule, tool routing (in order) and mutation safety.
brain-os copilot-instructions.md
Instructions for brainOS-HQ/brain-os, covering github copilot instructions, read this first, critical rules (also in agents.md) and known bugs (v0.4.1 fixes pending).
brain-os CLAUDE.md
Instructions for brainOS-HQ/brain-os, covering claude.md, agent instructions, build / dev, publish flow and project memory.
Lians copilot-instructions.md
Instructions for Lians-ai/Lians: Lians Guard is the current-state and completion guard for AI coding agents. Keep the primary product loop focused on four results: RECOVERED, STALE, BLOCKED, and READY FOR HUMAN REVIEW.