← ClaudeAtlas

workflow-inspectlisted

Appends the cost half to a workflow-retro record: parses the feature session's Claude Code transcripts with a bundled read-only script (tokens per agent, wall-clock, handoff tax) and writes the result into the record's Cost section. Companion of /workflow-retro; run it while the transcripts still exist (they are pruned after Claude Code's retention window, ~30 days by default). Requires python3.
cunhaax/ai-workflow · ★ 5 · AI & Automation · score 75
Install: claude install-skill cunhaax/ai-workflow
# /workflow-inspect — Compute the Feature's Workflow Cost Run this skill after `/workflow-retro` has recorded a feature's outcome, and within the transcript retention window. It fills the record's pending `## Cost` section with numbers computed from the raw session transcripts: tokens and wall-clock per sub-agent, the sub-agents' share of the total, and the handoff tax (files the planner read that the main agent re-read). Together the two halves say what each workflow step cost *and* caught — the evidence base for tuning the workflow (see *Evolving the System* in the AI Workflow plugin's own documentation). **Ground rules:** - **Numbers come from the script, verbatim.** Never estimate, adjust, or fill in a figure the script did not print. If the script fails or its output carries warnings, surface them to the user as-is (Rule 2 in `AGENTS.md` applies to the script like any other command). - **The only mutation is the log file.** Replacing the `## Cost` section of the chosen record(s) — after the user confirms — is the only write this skill performs. Never commit anything; `.workflow-log/` stays local. - The bundled script (`inspect.py`, in this skill's directory) is **read-only**: it parses transcripts and prints markdown to stdout. ## Step 1 — Pick the record(s) Resolve the log directory exactly as `/workflow-retro` does: `.workflow-log/` under the main worktree (parent of `git rev-parse --path-format=absolute --git-common-dir`). List the records whose `## C