Claude Code Telemetry and Logging Mods

Git Diff timeline above the prompt: click a commit to see it, click two to compare them, with their commit messages; a Branches tab compares two…

Log your reps: commits and passing tests build streaks and personal records

A side pane that shows Claude Code's agent loop as it runs: every hook event, a flow chart of the loop, a span timeline of each turn, and the tokens…

Tells implemented apart from verified: a requirement contract from your own words, a Mirage Detector for fake completeness, evidence from real…

Logs what fast-jev-compaction does (outcomes, TypeSafe requests, compactions, hook failures) to JSONL files

Per-session log of Claude's file changes, with Keep and Undo per file

Pane with the Lagoon project's environments: build status, build log links, last build, and links to each service

Unofficial Claude Code mod for Laravel apps (not affiliated with Laravel LLC): live log and queue monitoring, managed queue/Vite/scheduler, artisan…

Open lens traces (J-lens, logit lens) in a terminal viewer beside the agent, in tmux

Logs every MCP tool call and flags likely MCP gaps: browser fallbacks, tool errors, and answers that say the MCP can't do something

A live pane: context ring, session cost, a colored timeline of every tool call, files edited, and a sports-commentator recap of each turn

Classifies each turn as mechanical, ordinary or hard and routes it to a matching model and reasoning effort, logging every decision

Picks the model and effort for every subagent by having your session's own model judge the task, instead of a fixed model per agent type

A firewall for other mods: shows what each mod can reach as it loads, and audits, holds or refuses it by your policy

Pane listing every network connection this session made, traced back to the prompt and command that caused it

A live node map of every host your agent reaches: packets fly from your machine to github.com, npm, PyPI, MCP servers and unknown hosts, with a log…

Logs every function-hook event (on '*') to JSONL for inspection

OpenSpec lifecycle governance for Claude Code: stage band, fail-closed edit gate, task progress and an append-only execution log

Painel lateral com abas: tarefas, tokens e custo, log de ferramentas, arquivos alterados e notas

A project dashboard and isometric city map: progress, tasks, agents, resources, processes and skills

專案進度面板：從 GitHub milestone／issue／PR 與 git log 自動彙整目前專案的開發進度與里程碑。

Verifies signatures on the instruction files Claude Code loads, meaning CLAUDE.md, skills, and agent definitions, before they reach model context

Mod: self-facing /reasoning-review command, a scored, 12-metric engineering-skill assessment plus level estimate, from your own Claude Code sessions…

Attaches fresh React Native redboxes and native crash logs from running simulators and emulators to your prompt, and warns when an edit needs a…

Replay Theater: a live timeline of everything Claude does in a turn (commands, reads, searches, edits) with diffs and output

Roblox Studio safety layer for Claude Code (Studio MCP): RemoteEvent security audit, undo, Team Create protection, a confirmation before destructive…

A live pane for the background shell commands and monitors Claude runs

Session countdown with Pomodoro-style legs: status line, hidden time line for Claude, sound and toast at leg boundaries, leg log

Puts the iOS Simulator beside your Claude Code session: a live screenshot, dark mode and text size switches, your app's own logs, and tools that let…

Audit trail of skill invocations and file changes for Claude Code and Codex sessions

See which skills and plugins activated in your Claude Code session, what triggered them, and what they really cost in tokens (with prompt-cache…

Metrics-driven detection of AI-generated code slop for Claude Code

Acompanha em segundo plano os testes dos módulos cadastrados no workspace, com contadores observados, estado e logs por módulo

側邊欄的時間軸：這一輪的時間花在哪（等模型、想、寫、跑指令、網路、讀寫檔案、等幫手）。/timeline 開或關

A pane with one card per turn of the session: what you asked, what Claude did, what it touched

Folds each turn's tool calls into one line under the turn's closing line, with how long each took and the slowest highlighted

When a session ends, appends a one-line log entry to a markdown tracker file (e.g

ターンが終わるたびに使用率などを記録し、7日枠の目安（ペース表）との差を入力欄の下に出す

Keeps a ledger of what you asked for and counts it done only on evidence: claims stay pale until a read-back confirms them, bare SQL UPDATE or DELETE…

Compacts a long tool result through the AitherOS decision door before the model reads it: per LINE SHAPE, learned from outcomes, never dropping a…

Shows one short note above the prompt when a side check finds something about the work that the person very likely does not understand

Apple's Human Interface Guidelines inside Claude Code: Claude works with them in mind, each edit is checked against them, and an audit pane shows…

/tablero: ventas de Tiendanube + tráfico de Google Analytics + Meta Ads en un panel, con MER y conversión, sin gastar tokens

Masque secrets, emails et IP dans les logs, env et git log, et demande confirmation avant de lire un fichier sensible

A written log of your day with Claude: what you asked, when, and how long each took

Flight recorder for Databricks: every query, script and guardrail block Claude makes, in a band above the prompt and a per-session HTML trace with…

Claude logs its judgement calls as it works; approve or reject each one with a comment from a side pane

Beobachtet nach jedem git push den Cloudflare-Build (Workers Builds), zeigt den Stand unter dem Prompt, gibt Claude bei einem roten Build das Log und…