Recall Metrics — Development skill for Claude Code
Show total-recall metrics summary — sessions, tokens, top corrections, busiest project, longest session — over a window.
How to install Recall Metrics
Installs to ~/.claude/skills/88plug-total-recall-recall-metrics/SKILL.md
mkdir -p ~/.claude/skills/88plug-total-recall-recall-metrics && curl -fsSL https://raw.githubusercontent.com/88plug/total-recall/HEAD/commands/recall-metrics.md -o ~/.claude/skills/88plug-total-recall-recall-metrics/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Recall Metrics does
description: Show total-recall metrics summary — sessions, tokens, top corrections, busiest project, longest session — over a window. argument-hint: [since (e.g. 7d, 30d) — defaults to 7d]
Run `bash "${CLAUDE_PLUGIN_ROOT}/scripts/recall-cli.sh" metrics summary --since ${ARGUMENTS:-7d}` via Bash.
Present the output to the user verbatim. If the user asks for trends across windows, run with different `--since` values (7d, 30d, 90d) and compare.
Common follow-ups:
- "Which sessions cost t
Alternatives in Development
- Ccusage — CLI for analyzing Claude Code/Codex usage from local JSONL files 11.8k ★
- Crypto Market Rank — Query crypto market rankings including trending tokens, smart money inflows, meme rankings, and top trader PnL 483 ★
- Tmux Claude Hatch — tmux plugin that runs Claude Code sessions in popups per project directory, with an fzf picker showing each se 381 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Recall Status
Show total-recall index health — DB size, session count, last ingest, top topics for this cwd.
Recall Operator Context
One-shot operator briefing for this cwd — identity, active goal, top decisions, bans, voice cheats, recent cor
Claude Session Recall
A Claude Code skill that reads your session's own transcript, so a fact that arrived through a compaction summ
Orch Stats
Show orchestrator metrics — gate denials, routing mix by class and tier, spawns per session, clarify misses —
Hook Hero Stats
Show a quick summary of recent agent session activity.
Continuous Improvement
Reflect on the current session, analyze observations for patterns, and show instinct status. Runs on-demand to
Related Agents
Session Error Analyzer
Analyzes specific AI IDE sessions (Claude Code, OpenAI Codex, OpenCode) for LLM behavior errors and returns a
Recall
Runs the recall CLI over the user's past Claude Code sessions and returns the one actionable item — a command,
Teamai Recall
Search the team knowledge base (skills + learnings + docs + rules + codebase graph) and return a compact, stru