skills/work-log/SKILL.md
Use when you need to query work tracker events by recency, agent, or session.
npx skillsauth add seokan-jeong/team-shinchan team-shinchan:work-logInstall 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.
View and query events from the work tracker log.
/team-shinchan:work-log # Last 20 events
/team-shinchan:work-log --last 50 # Last 50 events
/team-shinchan:work-log --agent bo # Events for agent bo
/team-shinchan:work-log --type file_change # Only file_change events
/team-shinchan:work-log --session session-1234-abcd # Events for session
| Arg | Default | Description |
|-----|---------|-------------|
| --last N | 20 | Number of recent events to show |
| --agent {name} | (all) | Filter by agent name |
| --type {event_type} | (all) | Filter by event type |
| --session {id} | (all) | Filter by session ID |
Read .shinchan-docs/work-tracker.jsonl
If file doesn't exist:
No work tracker log found.
Events will be recorded automatically during Claude Code sessions.
{"ts","type","agent","session","data"}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Work Log ({N} events)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
{ts} | {type} | agent:{agent} | {data summary}
{ts} | {type} | agent:{agent} | {data summary}
...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Total: {total} events in log
Showing: last {N} (filtered: {filters applied})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Type | Source | Description |
|------|--------|-------------|
| session_start | SessionStart hook | New Claude Code session |
| session_end | SessionEnd hook | Session ended |
| agent_start | SubagentStart hook | Agent invoked |
| agent_done | SubagentStop hook | Agent completed |
| delegation | PostToolUse (Task) | Agent delegated to another |
| file_change | PostToolUse (Edit/Write) | File created or modified |
| tool_use | PostToolUse (other) | Other tool used |
| user_prompt | UserPromptSubmit | User sent a prompt |
| stop | Stop hook | Execution stopped |
.shinchan-docs/work-tracker.jsonl.jsonl.gz).shinchan-docs/.session-iddevelopment
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, a completeness critic, and a schema-validated rubric judge. Opt-in main-loop Workflow tier.
data-ai
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
testing
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
development
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.