src/orchestrator/skills/observability-logging/SKILL.md
Logs sessions, tracks activity, records delegation decisions, and stores review/dispute outcomes as NDJSON audit trails. Use when logging session activity, tracking work, recording decisions, building audit trails, capturing delegation history, or running pre-response verification checklists. Trigger terms: log, track activity, audit trail, session record, delegation log, NDJSON
npx skillsauth add monkilabs/opencastle observability-loggingInstall 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.
⛔ HARD GATE. Every agent MUST log every session to
events.ndjsonbefore responding. No exceptions. Session without logs is a failed session.
| File | Event types | Who | When |
|------|------------|-----|------|
| events.ndjson | session, delegation, review, panel, dispute | All agents / Team Lead / Panel runner | After each applicable event |
See .opencastle/logs/README.md for full schema.
Use opencastle log CLI. One record per task; never batch-log retrospectively.
Session (ALL agents, EVERY session):
opencastle log --type session --agent Developer --model claude-opus-4-6 \
--task "Fix login redirect bug" --outcome success --duration_min 15 \
--files_changed 3 --retries 0
Delegation (Team Lead, after each delegation — never batched):
opencastle log --type delegation --session_id feat/prj-57 --agent Developer \
--model claude-sonnet-4-6 --tier quality --mechanism sub-agent \
--tracker_issue PRJ-57 --outcome success --retries 0 --phase 2 \
--file_partition "src/components/"
modelandtiermust reflect the delegated agent's assignment from the agent registry.
Review (Team Lead, after each fast review):
opencastle log --type review --tracker_issue PRJ-42 --agent Developer \
--reviewer_model gpt-5-mini --verdict pass --attempt 1 \
--issues_critical 0 --issues_major 0 --issues_minor 2 \
--confidence high --escalated false --duration_sec 45
Panel (Panel runner, after each vote):
opencastle log --type panel --panel_key auth-review --verdict pass \
--pass_count 3 --block_count 0 --must_fix 0 --should_fix 3 \
--reviewer_model claude-opus-4-6 --weighted false --attempt 1 \
--tracker_issue PRJ-42 --artifacts_count 5
Dispute (Team Lead, after each dispute):
opencastle log --type dispute --dispute_id DSP-001 --tracker_issue PRJ-42 \
--priority high --trigger panel-3x-block --implementing_agent Developer \
--reviewing_agents "Reviewer,Panel (3x)" --total_attempts 6 --status pending
Verify any append: tail -1 .opencastle/logs/events.ndjson
⛔ STOP. Verify before responding — fix any missing log NOW.
.opencastle/LESSONS-LEARNED.md read at session startevents.ndjson has a session record (ALWAYS)delegation record per delegation (Team Lead) (if applicable)review record per fast review (if applicable)Inherits: base-output-contract
development
Defines 10 sequential validation gates: secret scanning, lint/test/build checks, blast radius analysis, dependency auditing, browser testing, cache management, regression checks, smoke tests. Use when running pre-deploy validation or CI checks, CI/CD pipelines, deployment pipeline validation, pre-merge checks, continuous integration, or pull request validation.
development
Generates test plans, writes unit/integration/E2E test files, identifies coverage gaps, flags common testing anti-patterns. Use when writing tests, creating test suites, planning test strategies, mocking dependencies, measuring code coverage, or test planning.
development
Provides model routing rules, validates delegation prerequisites, supplies cost tracking templates, defines dead-letter queue formats for Team Lead orchestration. Load when assigning tasks to agents, choosing model tiers, starting delegation session, running multi-agent workflow, delegating work, choosing which model to use, or assigning tasks.
testing
Saves, restores session state including task progress, file changes, delegation history. Use when saving progress, resuming interrupted work, picking up where you left off, or checkpointing current work.