Friction Report — Development skill for Claude Code
Show where exit-status-guard friction accumulates, from your local Claude Code session transcripts.
How to install Friction Report
Installs to ~/.claude/skills/karlkfi-claude-exit-status-guard-friction-report/SKILL.md
mkdir -p ~/.claude/skills/karlkfi-claude-exit-status-guard-friction-report && curl -fsSL https://raw.githubusercontent.com/karlkfi/claude-exit-status-guard/HEAD/commands/friction-report.md -o ~/.claude/skills/karlkfi-claude-exit-status-guard-friction-report/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Friction Report does
description: Show where exit-status-guard friction accumulates, from your local Claude Code session transcripts. argument-hint: "[--since 24h] [--repo name] [--raw] [--json] [--top N]" allowed-tools: Bash
The exit-status-guard friction report below is generated by re-reading the hook decisions Claude Code already recorded in your local session transcripts (it adds no telemetry — see PRIVACY.md). Show it to me verbatim, then add at most one sentence naming the rule that fires most and wh
Alternatives in Development
- Telegram — Show Telegram bot status and manage global session 1.3k ★
- Poirot — 96 macOS app for browsing Claude Code sessions, viewing diffs, and re-running commands 104 ★
- Enable Auto Save — Enable automatic session save on exit (Registers SessionEnd hook) 30 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Drift Guard
Run every drift guard and report the exit codes observed this run.
Wait
Wait for a wchat run to finish, then report its final status and exit code
Agent Session Status
Live OpenCode, Claude Code, and Codex session state for Ironbar and Waybar. Provider events are reduced to a s
Aef Fresh Install Onboarding
Install AEF on a machine and onboard a new/empty project — dogfood-hardened (T-2441): project-local fw, sessio
Claude Secretmode
Leave-no-trace ephemeral Claude Code sessions on macOS — runs Claude Code on a RAM disk so transcripts, prompt
Deep Recall
Deep semantic search over the ENTIRE vault (2k+ notes incl. session-log, handoffs, transcripts, graph) via the
Related Agents
Release Failure Analyzer
MUST BE USED when release.yml fails (Phase 3 of releasing-erfana skill, on non-zero gh run watch --exit-status
Delivery Engineer
Writes WORKFLOW.md, SOP.md, and 07-runbook.md for a system that calls a language model. Dry-runs every runbook
Transcript Miner
Use when mining Claude Code transcripts for friction — where the tooling was wrong — at the end of a work stre