srstomp/work-session
plugins/pokayokay/skills/work-session/SKILL.md
Use when starting AI development sessions, resuming interrupted work, managing multi-session projects, or orchestrating work with human checkpoint control (supervised, semi-auto, auto, or unattended modes).
$ install --global
skillsauthnpx skillsauth add srstomp/pokayokay work-sessionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 27, 2026, 7:06 AM40.4s18 files scanned
SKILL.md
- name:
- work-session
- agents:
- [yokay-brainstormer, yokay-implementer, yokay-fixer, yokay-spec-reviewer, yokay-quality-reviewer, yokay-browser-verifier, yokay-test-runner]
- description:
- Use when starting AI development sessions, resuming interrupted work, managing multi-session projects, or orchestrating work with human checkpoint control (supervised, semi-auto, auto, or unattended modes).
Work Session
Orchestrate AI-assisted development with configurable human control, using ohno for task management via MCP.
When NOT to Use
- Planning work — Use
planningto create epics/stories/tasks before starting sessions - Quick one-off tasks — Use
/quickfor simple tasks that don't need the full subagent pipeline - Revising a plan — Use
plan-revisionto modify scope, dependencies, or task hierarchy - Running a spike — Use
spikefor time-boxed investigation before committing to implementation
Key Principles
- Fresh context per task via subagent dispatch (no context degradation)
- Configurable checkpoint control: supervised, semi-auto, auto, or unattended
- Smart worktree isolation by task type (feature/bug → worktree, chore/docs → in-place)
- Hooks handle lifecycle automatically (sync, commit, tests)
- ohno MCP provides session continuity across conversations
- Evidence before completion claims (
verification-before-completion) - Root-cause-first bug handling (
systematic-debugging) - Explicit branch finish choice: merge, PR, keep, or discard (
finishing-branch) - Token-aware dispatch: stay inline for tiny work, use focused agents when isolation or parallelism is worth the cost
Quick Start Checklist
- Initialize ohno:
npx @stevestomp/ohno-cli init - Get session context: MCP
get_session_context() - Get next task: MCP
get_next_task() - Dispatch subagent for implementation
- Review results at checkpoints (based on mode)
Operating Modes
| Mode | Task Complete | Story Complete | Epic Complete | |------|--------------|----------------|---------------| | supervised | PAUSE | PAUSE | PAUSE | | semi-auto | log | PAUSE | PAUSE | | auto | skip | log | PAUSE | | unattended | skip | skip | skip |
References
| Reference | Description |
|-----------|-------------|
| subagent-dispatch.md | Coordinator vs implementer roles, dispatch mechanics |
| session-protocol.md | Session start/end checklists, MCP workflow |
| checkpoint-types.md | PAUSE, REVIEW, NOTIFY checkpoint patterns |
| skill-routing.md | Task type to skill mapping |
| operating-modes.md | Supervised, semi-auto, auto, unattended details |
| worktree-management.md | Setup, completion, merge/PR workflows |
| parallel-execution.md | Parallel Execution: benefits, tradeoffs, dependency handling |
| hook-integration.md | Work loop with hooks, mode-specific behavior |
| ohno-integration.md | MCP tools and CLI commands reference |
| error-recovery.md | Build failures, blocked tasks |
| approval-policy.md | Runtime approval defaults for safe pokayokay automation |
| token-budgeting.md | Token/context budgeting rules for agents, skills, parallelism, and handoffs |
| anti-patterns.md | Common mistakes and fixes |
| bug-fix-pipeline.md | Agent pipeline for /fix --thorough and /hotfix commands |
| pre-flight-checks.md | Checks run before unattended/headless sessions |
Related Skills
srstomp/worktrees
development
VerifiedTrustedCommunity
Git worktree management for isolated task development
6SKILL.mdUpdated Apr 27, 2026
srstomp/verification-before-completion
testing
VerifiedTrustedCommunity
Use before claiming work is done, fixed, passing, ready to commit, ready to PR, or ready to mark complete. Requires fresh verification evidence and explicit command output before success claims.
6SKILL.mdUpdated Apr 27, 2026
srstomp/testing-strategy
development
VerifiedTrustedCommunity
Use when designing test architecture, building API test suites, validating API contracts, setting up component or E2E testing, managing test data, debugging flaky tests, reviewing coverage strategy, or organizing test files. Covers test pyramid, mocking (MSW), frontend (React Testing Library, Playwright), and CI integration.
6SKILL.mdUpdated Apr 27, 2026
srstomp/systematic-debugging
development
VerifiedTrustedCommunity
Use when diagnosing bugs, failing tests, build failures, unexpected behavior, flaky tests, regressions, or production incidents. Requires reproduction, root cause evidence, one-hypothesis fixes, and regression verification before editing.
6SKILL.mdUpdated Apr 27, 2026