audit-orphan-runs
Identifies abandoned worktrees and stale runs (no events for >2h, status=running) to flag for cleanup.
Use when the user wants to inspect the result branch of a completed WISP run — shows files in the result branch, the per-task git log graph, and a brief summary. Trigger on phrases like "what did harness produce", "show the run output", "inspect the result branch".
$ npx -y skills add Samuel0101010/wisp-orchestrator --skill wisp-inspect --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/wisp-inspectContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user wants to inspect the result branch of a completed WISP run — shows files in the result branch, the per-task git log graph, and a brief summary. Trigger on phrases like "what did harness produce", "show the run output", "inspect the result branch".
name: wisp-inspect description: Use when the user wants to inspect the result branch of a completed WISP run — shows files in the result branch, the per-task git log graph, and a brief summary. Trigger on phrases like "what did harness produce", "show the run output", "inspect the result branch".
Show what a WISP run produced. Works on completed runs (success or failure) by inspecting the per-run git branches in the project's repo.
> **Platform note**: `git` itself is cross-platform; only the `grep` line below has a PowerShell variant. The bash form also runs from Git Bash / WSL on Windows.
1. **Resolve the runId to its repoPath**:
2. **List branches matching the runId**:
# bash git -C <repoPath> branch --all | grep <runId-first-8-chars>
# PowerShell git -C <repoPath> branch --all | Select-String "<runId-first-8-chars>"
Expect to see: `harness/<runId>/<task1>`, `harness/<runId>/<task2>`, ..., `harness/<runId>/result` (if the run succeeded). Replan runs ALSO have `v2/`, `v3/` prefixed branches — list them too.
3. **Show the git log graph** for these branches:
git -C <repoPath> log --oneline --graph harness/<runId>/result harness/<runId>/<task-leaves...>
This visualises which tasks ran in which order and where they merged.
4. **List files in the result branch**:
git -C <repoPath> ls-tree -r --name-only harness/<runId>/result
Filter out node_modules and other large irrelevant trees.
5. **Per-task summary** (optional, takes longer): For each task branch, show the diff against its parent:
git -C <repoPath> log --stat -1 harness/<runId>/<taskId>
Visual team-builder, plan-as-artifact, and live execution graph for autonomous Claude Code agent crews. Spawn a 3-role team, generate a DAG plan, run for hours, watch it ship in your browser.
Repo: Samuel0101010/wisp-orchestrator
Identifies abandoned worktrees and stale runs (no events for >2h, status=running) to flag for cleanup.
Drafts a docs/solutions/YYYY-MM-DD-<slug>.md entry for a recently completed run, capturing problem/solution/lessons.
Working discipline for code-writing agents — read before edit, smallest correct change, run the gates before claiming done. Injected into builder roles' system…
Conducts focused research on a topic by reading project files, searching memory, and synthesizing findings into a structured report.
Self-diagnostics for the harness — checks DB integrity, MCP wiring, claude binary availability, and recent run failures.
Visual + interaction quality bar for frontend roles — states, responsiveness, accessibility, consistency. Injected into frontend roles' system prompts.