Lens CLAUDE.md

Project instructions for Lens, an Electron desktop app that searches and resumes local Claude Code and OpenAI Codex session history.

In plain words
What is it for?
They help developers run Lens locally, build releases for macOS, Windows, or Linux, inspect its architecture, and regenerate its icon.
Why use it?
They explain the project's structure and the commands needed to type-check, build, package, and check translations.

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/maliming/lens/claude-md
Clone the repo
git clone --depth 1 https://github.com/maliming/Lens
Per session 5,458 This file is loaded in full into every session.
When invoked 5,458 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 $0.05458 $0.05458
Opus 5 $0.02729 $0.02729
Sonnet 5 $0.01092 $0.01092
Haiku 4.5 $0.00546 $0.00546

Measured 2d ago against content hash 76a26232aee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Lens 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 2d 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 · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 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

Lens is an Electron desktop app that browses, searches, and resumes local Claude Code (~/.claude/projects/*.jsonl) and OpenAI Codex (~/.codex/sessions/**/*.jsonl) session history. The package name in package.json is lens.

Common commands

npm install
npm run dev          # Vite (http://localhost:5173) + Electron in parallel
npm run typecheck    # tsc --noEmit (run before any commit)
npm run check:i18n   # scripts/check-i18n.mjs — diffs each locale vs en
npm run build        # typecheck + Vite build → dist/  (does NOT package)
npm run preview      # run Electron against built dist/

npm run dist:mac     # release/Lens-<ver>-(arm64|x64).zip
npm run dist:win     # release/Lens-<ver>-win.zip
npm run dist:linux   # release/Lens-<ver>-linux-x86_64.AppImage

npm run build:icon   # regenerate build/icon.{icns,ico,png} from icon.svg
DEMO_BUILD=1 npm run dist:mac   # screenshot-ready build with fake data forced on

There are no tests and no linter configured. npm run build runs tsc --noEmit && vite build. npm run check:i18n is NOT in build — running it reveals real gaps (non-English locales miss ~200 keys each); wire to CI only after you've committed to translating, otherwise it'll fail every build.

Renderer hot-reloads under npm run dev. Main-process edits (electron/main.cjs) require a full restart — there is no main-process reload. Session cache manifests (sessions-cache-claude.json / sessions-cache-codex.json, plus bounded shards when a source exceeds the single-file limit) under the platform userData directory survive across restarts. Parser/cache schema changes require a versioned migration in electron/lib/sessions-cache.cjs; do not rely on manually deleting caches.

High-level architecture

Two-process boundary

  • electron/main.cjs (Node) — all filesystem IO, JSONL parsing, sub-process spawning (terminal launchers, claude/codex CLI probes), persistence (favorites.json / excludes.json / aliases.json / per-source session caches / app-prefs.json under app.getPath('userData')).
  • src/ (React 18 + TypeScript + Vite + Tailwind) — pure renderer. No Node access. Talks to main only via window.api.*.
  • electron/preload.cjscontextBridge.exposeInMainWorld('api', ...). This is the IPC contract; any new feature that crosses the boundary needs an entry here + a matching ipcMain.handle in main.cjs + a typed signature in src/types.ts under declare global { interface Window { api: { ... } } }.

Read the full file on GitHub · 229 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. 2d ago First seen · 229 lines · 5,458 tokens per session scan A 76a26232aee7

Subscribe to this mod's changes

Lens CLAUDE.md is an instructions file published in the GitHub repository maliming/Lens (6 stars, last pushed 10d ago), licensed MIT. It adds 5,458 tokens to every session, about $0.0273 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

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

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

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 · 4,345 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

next.js 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