Claude Code mod
debrief
Records metadata-only session telemetry (tokens per model and loop, turns, agents, friction) for project after-action reviews.
Install
/plugin marketplace add matrix-freed/debrief
/plugin install debrief@debriefMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, writes files, drives Claude, reads files, reads env vars, reads mod state, persists state, draws
- Sees
- classic hooks, subagent spawns, every tool call, every skill
- Hooks
session.startclassic.SessionStartclassic.InstructionsLoadedturn.startturn.stepturn.completeagent.spawntool.callclassic.PostToolUseFailureclassic.PreCompactskill.promptcommand.runsession.sendsession.receivesession.measuresession.end
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- matrix-freed/debrief
- Folder
debrief- Marketplace
debrief- Author
- debrief
- License
- MIT
- Last updated
- 29 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is debrief?
Records metadata-only session telemetry (tokens per model and loop, turns, agents, friction) for project after-action reviews. It is a mod for Claude Code, from matrix-freed/debrief on GitHub.
What can the debrief mod access?
Its widest reach is "writes or runs" (runs processes, writes files, drives Claude, reads files, reads env vars, reads mod state, persists state, draws). It sees classic hooks, subagent spawns, every tool call, every skill. Like any mod, it runs with your permissions.
How do I install debrief?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add matrix-freed/debrief and then /plugin install debrief@debrief.
More context & usage mods
cyclops-fresheye
CyclopsEyeTeam/cyclops-fresheye
Fresh eyes on your work: the same model reviews it in a fresh context, without CLAUDE.md, memory or hook context, then you switch back with nothing lost.
deck
joharraza/claude-deck
One band above the prompt for Limit Radar, Baton and Workbench: liquid gauges for the 5-hour and 7-day limits and the context, a live git graph (a small radar and tank when no repository is open), and one message with its buttons when something needs you.
cubeman
eunille/Claude-mod
Cubeman for Claude Code: a live pane of skills, tools, subagents, context, tokens and activity, a pixel mascot that acts out what Claude is doing (classic, or Arbitrage with guns and zombie waves), and a plan-first workflow that waits for your approval.
desk-meter
nakadaharuki/desk-meter
Context usage, branch and tool count in a band; tokens per request charted in a pane; a note tool for Claude and a check before dangerous commands. English and Japanese
ctx-usage-dock
seanmars/my-agent-plugins
A docked pane and a status line that break the context window down by category: messages, skills, MCP tools, memory files, rules and agents
deskbar
0NE-C0DEMAN/deskbar
A desk for the Claude Code prompt: context weather, Gmail, calendar, tasks across sessions, notes, a music deck and a billable-hours timer
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.