From bkit — AI Native Development OS
View audit logs, decision traces, and session history for AI transparency. Supports log, trace, summary, and search subcommands.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bkit:audit [log|trace|summary|search] [query][log|trace|summary|search] [query]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
> User-invocable skill for viewing audit logs, decision traces, and session history.
User-invocable skill for viewing audit logs, decision traces, and session history.
| Argument | Description | Example |
|---|---|---|
| (none) | Show recent audit log entries (same as log) | /audit |
log | Show recent audit log entries (last 20) | /audit log |
trace <feature> | Show decision traces for a feature | /audit trace user-auth |
summary | Show daily/weekly audit summary | /audit summary |
search <query> | Search audit logs by action type, feature, or date | /audit search "phase_transition" |
Display recent audit log entries.
.bkit/audit/YYYY-MM-DD.jsonlJSONL Entry Schema:
{
"timestamp": "2026-03-19T10:30:00.000Z",
"action": "phase_transition",
"feature": "user-auth",
"from": "plan",
"to": "design",
"automationLevel": "semi-auto",
"triggeredBy": "user",
"details": "Plan approved, transitioning to Design"
}
Output Format:
--- Audit Log (Last 20 Entries) -------------------
[2026-03-19 10:30] phase_transition | user-auth
plan -> design (Semi-Auto, user-triggered)
[2026-03-19 10:25] checkpoint_created | user-auth
Checkpoint cp-1710842700000 before Design phase
[2026-03-19 10:20] automation_level_changed | -
L1 -> L2 (trust score: 72)
...
---------------------------------------------------
Total entries today: 45
Show decision traces for a specific feature.
.bkit/decisions/YYYY-MM-DD.jsonlDecision Trace Entry Schema:
{
"timestamp": "2026-03-19T10:30:00.000Z",
"feature": "user-auth",
"decision": "advance_to_design",
"rationale": "Plan document complete, matchRate N/A at this phase",
"alternatives": ["request_plan_revision", "skip_to_do"],
"chosenBecause": "Plan deliverable exists and passes validation",
"automationLevel": "semi-auto",
"confidence": 0.92
}
Output Format:
--- Decision Trace: user-auth ---------------------
[10:15] START -> pm
Decision: Begin PDCA cycle
Rationale: New feature request detected
[10:20] pm -> plan
Decision: advance_to_plan
Rationale: PRD document generated successfully
Alternatives: [reject_prd, revise_scope]
Confidence: 0.88
[10:30] plan -> design
Decision: advance_to_design
Rationale: Plan document complete, passes validation
Alternatives: [request_plan_revision, skip_to_do]
Confidence: 0.92
---------------------------------------------------
Total decisions: 3
Show daily or weekly audit summary.
Output Format:
--- Audit Summary (2026-03-19) --------------------
Total Actions : 45
Phase Transitions : 12
Checkpoints Created : 4
Errors Recorded : 1
Recoveries : 1
Action Breakdown:
phase_transition : 12 (27%)
checkpoint_created : 4 (9%)
match_rate_recorded : 8 (18%)
automation_level_change: 2 (4%)
iteration_completed : 6 (13%)
other : 13 (29%)
Automation Ratio: 67% auto / 33% manual
Trust Score Change: +3 (69 -> 72)
---------------------------------------------------
Weekly Trend (last 7 days):
Mon: 32 actions | Tue: 45 actions | Wed: 28 actions
...
Search audit logs by action type, feature name, or date range.
phase_transition), filter by action.bkit/audit/Search Examples:
# Search by action type
/audit search "phase_transition"
# Search by feature name
/audit search "user-auth"
# Search by date
/audit search "2026-03-18"
# Full-text search
/audit search "error"
| Path | Format | Purpose |
|---|---|---|
.bkit/audit/YYYY-MM-DD.jsonl | JSONL | Daily audit log entries |
.bkit/audit/summary/ | JSON | Pre-computed daily/weekly summaries |
.bkit/decisions/YYYY-MM-DD.jsonl | JSONL | Decision trace entries |
| Module | Function | Usage |
|---|---|---|
lib/audit/audit-logger.js | readAuditLog() | Read audit entries |
lib/audit/audit-logger.js | searchAuditLog() | Search/filter entries |
lib/audit/decision-tracer.js | getDecisionTrace() | Read decision traces |
# View recent log entries
/audit
# View decision trace for a feature
/audit trace user-auth
# View daily summary
/audit summary
# Search for phase transitions
/audit search "phase_transition"
# Search by feature
/audit search "user-auth"
npx claudepluginhub popup-studio-ai/bkit-claude-code --plugin bkitDebugs and inspects LLM/AI agent traces using PostHog's MCP tools. Handles trace/session URLs, event hierarchies, and SQL queries for token usage and agent behavior analysis.
Queries AI decision trails for code reviews (CRs), gates, analysis (intent/change/risk/autonomy), architecture decisions (ADR), and timelines. Audits judgments with confidence scores, processes, and context navigation.
Audits Claude Code session logs for PBR workflow compliance (STATE.md updates, hooks, commits, skills) and UX quality (flows, friction, expectations). Supports date ranges and modes.