Claude Code Telemetry and Logging Mods

A debugger for Claude Code tool calls: breakpoints, pause/continue/reject/step, a timeline, an inspector, Error Lens failure diagnosis, a Permissions…

Sets the main conversation's reasoning effort per prompt with TypeSafe's Jev (via OpenRouter), reading recent conversation context

A Servers pane for this project's dev servers: what is listening, on which port, since when, with Start, Stop, Restart and Log buttons; names the…

Above the prompt: the branch PR with its checks and failing log lines, uncommitted work with a commit-and-push key, and how far the branch is behind…

Ships a feature only when a test that actually ran proves every requirement in its spec

A daily bodyweight rep goal inside Claude Code: log with /fit, quick-log band, long-turn nudges, streaks and a score grid, optional strict mode

Live work panel: phase checklist, progress strip above the prompt, jobs, helpers and recent activity

Every event of the session, tool calls and their full results included, appended to a JSONL file per session

See what Claude changed, turn by turn

Drive chottag (c-hottag) from Claude Code: switch the serving account, set the remote account, log accounts in, check limits and the install

cliamp radio in Claude Code: sidebar with favorites, search and discovery, mini player, song log, focus mode, ducking and a radio tool for Claude

Animated cockpit for Claude Code: live session activity (model, effort, mode, limits, context) and a timeline of the execution plan

Star-topology observability for subagents: observed, declared and verified progress, SendMessage tracking, and animated pixel crabs with shared…

Depois de cada push do Claude, acompanha o commit no GitHub (Actions, Vercel, Cloudflare, Netlify), acha a URL publicada, testa se ela responde e…

Replaces context compaction in the controller's interactive session of a log-driven repo: the conversation is rebuilt from .context/events.jsonl by…

Headroom: rate-limit countdowns and a burn-rate forecast for Claude Code

Context-size meter, noisy tool-output pruning and a cost audit for Claude Code, using OpenAI Decisions (gpt-6-luna)

A cinematic HUD: live radar sweep, threat level and telemetry feed of everything Claude does

Live progress of every long-running job above the Claude Code prompt: bars, speed, ETA, stall and crash detection

A pane that shows live what Claude is doing: the turn's phase, the last tool, and every file it touched

このセッションで変更したファイルと実行したコマンドを横のパネルに一覧で出す

Trilha de auditoria do Claude Code no Adaflow: /adaflow login (device flow) e envio em lote so de metadados (sessao, turno, ferramenta negada)

Audits a URL for AI answer engines (ChatGPT search, Perplexity, Google AI Overviews, Copilot, Claude): crawler access, firewall, indexing directives…

Tracks each subagent's model, tokens, tools and time, scores whether a cheaper model would have done, and keeps a bounded per-repo log under…

A box above the prompt that always says what the agent is doing right now, alive with color and motion: an animated status glyph, a glowing jellyfish…

Allan's workflow mods, built from his own session logs

A side pane that draws the architecture of what you're building, version by version: what changed and why, a request traced through it, a design…

Claude logs the assumptions it makes mid-build; a band above the prompt expands into a list where you mark each Right or Wrong

Macros no prompt: @diff, @branch, @log e @clip anexam o diff, o histórico ou a área de transferência antes do modelo ler

sign up or log in, an attentionfarm band above the prompt and a scrolling status line for claude code

Turns build, test and lint output from tsc, cargo, go, pytest, jest, gradle and more into a live pane of errors by file, and hands Claude the…

After a carousel render: Caption, Queue Threads and Log ledger buttons; blocks Threads posts with a part over 500 characters

PR checks and GitHub Actions runs, live in Claude Code

Asks a local Clef decision model whether an expensive tool call or subagent is actually needed before Claude Code pays for it

Logs your time, Claude's time and your 5-hour/weekly usage per client, so client work is easy to bill and budget

Bill clients for Claude Code work: per-client time, tokens and proof of work, exported as invoice-ready logs

Mask client names, personal data and secrets before anything leaves this machine; keep the list private and leave no trace of what was swapped

Status line: progress of the newest long-running job log (count and time left only, never its output)

Logs every shell command the agent runs and, only when you ask, explains why it ran each one and what it does

Context-window gauge with a pre-compaction warning, and a log of what was in flight at each compaction

Cutroom: a cutting-room pane for HyperFrames projects inside Claude Code — frame preview, timeline, trim/split/move/delete/undo, Studio selection…

Opens a CloudWatch metric widget as a live chart pane with range, pan, refresh and click-to-ask

Keeps decisions mentioned in replies in a band above the prompt until they are written to your decision log

Reviews Claude's observable decisions with a separate critic model and shows evidence-backed criticism cards you can accept, challenge, implement and…

Band above the prompt showing what the session's thinking is doing: focus, a turn timeline, and turn cost

Screen reader companion for Claude Code: detects VoiceOver, NVDA or JAWS, enables screen reader mode from the next start, delivers whole answers…

Picks the reasoning effort for each turn of the main conversation with a System One classifier (hosted Jev or a compatible service) and shows the…

Observe tool timing and outcomes without retaining arguments or output