adapters/openclaw/skills/clade-report/SKILL.md
Get session reports, cost breakdowns, and blocker details from Clade
npx skillsauth add shenxingy/claude-code-kit clade-reportInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Get detailed session reports, cost breakdowns, blockers, and skipped tasks.
User asks about:
Endpoint: GET {CLADE_BASE_URL}/report
Optional query: ?project=/path/to/project
Headers:
Authorization: Bearer {CLADE_API_KEY}
Response:
{
"project": "/home/user/myproject",
"report": "## Session: 2025-03-24 14:30 → 22:15 (465min)\n\n### Status: converged\n\n### Completed\n12 commits since session start.\n\n### Skipped (2 tasks)\n## Skipped: flaky integration test\nReason: External API timeout\n\n### Blockers (0)\nNone\n\n### Cost: $8.42\n\n### Iterations: 5\n\n### Feature: auth-middleware",
"cost_history": [
{"ITER": "1", "COST": "1.50", "CUMULATIVE": "1.50", "TASKS": "3", "DURATION": "8min"},
{"ITER": "2", "COST": "2.10", "CUMULATIVE": "3.60", "TASKS": "4", "DURATION": "12min"},
{"ITER": "3", "COST": "1.80", "CUMULATIVE": "5.40", "TASKS": "2", "DURATION": "6min"}
],
"blockers": "",
"skipped": "## [2025-03-24T18:30:00+0000] Skipped: flaky integration test\nReason: External API timeout during test run\nAttempted: Retry 3 times, all timed out"
}
📊 Session Report — {project name}
⏱️ {start time} → {end time} ({duration})
✅ Status: {status}
📈 Progress: {completed_count} commits in {iterations} iterations
💰 Total cost: ${cost}
{if cost_history:}
Cost per iteration:
Iter 1: ${cost} ({tasks} tasks, {duration})
Iter 2: ${cost} ({tasks} tasks, {duration})
...
{if skipped not empty:}
⏭️ Skipped tasks:
{skipped content, summarized to 2-3 lines max}
{if blockers not empty:}
⚠️ Blockers:
{blockers content, summarized to 2-3 lines max}
💰 Total: ${cumulative from last cost_history entry}
Last iteration: ${cost} for {tasks} tasks in {duration}
development
Orchestrate a fleet of parallel `codex exec` workers with you (Claude Code) as the supervisor — spawn one per isolated git worktree, dispatch headless, verify each INDEPENDENTLY, PR/merge. The manual "codex-ultracode" pattern for fanning out real implementation, research, or review work onto Codex. Bakes in the hard gotchas (stdin blocking, background tracking, don't-trust-self-reports, writer isolation). Triggers on — orchestrate codex, codex workers, codex fleet, spawn codex, delegate to codex in parallel, manual ultracode, 开 codex 小弟, 派 codex worker — NOT for a single cross-vendor opinion (use the `second-opinion-codex` agent), NOT for web-UI worker decomposition (use `/orchestrate`).
development
Create and manage git worktrees for parallel Codex sessions
development
Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Codex built-in /verify (which runs the app to observe a single change working) — this one walks the AGENTS.md "Features (Behavior Anchors)" list.
documentation
End-of-session documentation sync — updates TODO.md and PROGRESS.md only (run /commit after to commit everything)