Aggregate journal entries to surface patterns — recurring blockers, most-modified files, effective tools, and team velocity trends. Use for retrospectives, standups, or understanding project health.
From agent-journalnpx claudepluginhub brewpirate/zen-flow --plugin agent-journalThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Optimizes cloud costs on AWS, Azure, GCP via rightsizing, tagging strategies, reserved instances, spot usage, and spending analysis. Use for expense reduction and governance.
Analyze the journal to surface patterns across multiple sessions. Produces aggregate insights rather than individual entries — what keeps going wrong, what keeps working, where the effort is concentrated.
Announce at start: "Analyzing journal for patterns."
Reads from .claude/journal.jsonl in the project root.
/agent-journal:summary # last 7 days (default)
/agent-journal:summary week # last 7 days
/agent-journal:summary month # last 30 days
/agent-journal:summary all # everything
Count entries by type:
Activity (last 7 days):
work: 12 entries
bug-fix: 4 entries
refactor: 2 entries
exploration: 3 entries
review: 1 entry
audit: 1 entry
─────────────────────
Total: 23 entries
Files that appear most frequently across entries:
Most Modified Files:
1. packages/server/src/server/routes/api.ts (8 entries)
2. packages/core/src/core/context.ts (5 entries)
3. packages/frontend/src/components/ActivityLog.tsx (4 entries)
These are churn indicators — files touched repeatedly may need refactoring or better test coverage.
Extract and deduplicate blockers from entries:
Recurring Blockers:
- "Mock pollution in tests" (appeared 3 times)
- "Rate limiter config unclear" (appeared 2 times)
- "SSE connection timeout" (appeared 2 times, resolved 2026-03-27)
Resolved blockers (appear in later entries as fixes) are marked.
Aggregate the insights and wouldDoDifferently fields:
Top Insights:
- Two-stage review (spec + quality) catches different failure modes (3 mentions)
- Check installed package version before reading docs (2 mentions)
- Worktree delegation prevents context pollution (2 mentions)
Recurring "Would Do Differently":
- "Run full test suite earlier" (3 mentions)
- "Read existing tests before writing new ones" (2 mentions)
Which zen skills are used most:
Skills Usage:
zenflow:dispatch 8 sessions
zenflow:check-work 8 sessions
zenflow:collab 5 sessions
zenflow:bug-fix 4 sessions
zenflow:plan 3 sessions
zenflow:audit 1 session
## Journal Summary — last 7 days (23 entries)
### Activity
[breakdown by type]
### Hot Files
[top 5 most-modified files]
### Recurring Blockers
[deduplicated, with resolution status]
### Insights
[aggregated patterns from insights + wouldDoDifferently]
### Skills
[usage counts]
### Health Signals
- Bug-fix ratio: 17% (4/23) — [healthy < 25%]
- Workaround ratio: 9% (2/23) — [healthy < 15%]
- Blocker-free sessions: 78% (18/23)
Quick indicators derived from the data:
| Signal | Healthy | Warning | Unhealthy |
|---|---|---|---|
| Bug-fix ratio | < 25% | 25-40% | > 40% |
| Workaround ratio | < 15% | 15-30% | > 30% |
| Blocker-free sessions | > 70% | 50-70% | < 50% |
| Repeat blocker rate | < 10% | 10-25% | > 25% |
These are rough heuristics, not hard rules. A spike in bug fixes after a big feature is normal.