Support Storm
Simulate launch support load and identify fixes that reduce maintenance.
Decision Log
Record a technical or product decision, alternatives, and rationale for future agents.
Agent Log Forensics
Analyze Claude/Codex logs for behavior patterns, repeated friction, and Toolsmith gaps.
Status Copy Trust Audit
Audit CLI and app status wording, repeated-run behavior, and client label alignment.
Ralph Loop
Run repeatable multi-LLM hardening sweeps: review, fix, document, repeat.
Remote Host Verifier
Compare commands, versions, config, and behavior across local and SSH hosts.
Django Smoke Alarm
Run and triage Django/DRF security smoke checks before shipping or after scanner findings.
Empathy Audit
Review code through user, machine, developer, and support lenses.
Handle Pr
Handle GitHub PR comments: assess, fix approved findings, test, commit, and reply.
Contacts Unify
Merge and dedupe macOS, iCloud, Google, Zoho, or VCF contacts with reviewable provenance.
Visual Qa Loop
Run before/after visual QA for local UI changes with screenshots and concise findings.
Parallel Isolated App Testing
Plan isolated parallel test lanes for desktop apps and local tools with shared state.
First Contact
Red-team onboarding and first use to find confusion, broken expectations, and abandonment.
Release Operator
Run a CLI or app release: verify, version, test, publish, and verify installs.
Dependency Pinning
Audit Docker, CI, and language dependencies for SHA/digest pinning and cooldowns.
Launch Sequence
Run first-contact, support-storm, trust-audit, and pre-mortem for a launch verdict.
Profile Me
Create a personal AI profile, working guide, and compact assistant prompt.
Scope Hammer
Cut brainstorm output to a shippable MVP: delete, mock, reuse, or ship.
Trust Audit
Audit product trust: permissions, privacy, billing, file changes, and silent failures.
Post Mortem
Analyze a failure, find its cause, capture learnings, and prevent recurrence.
Changelog Writer
Draft plain-language changelog entries from Git history, optionally updating CHANGELOG.md.
Research Person
Research a person from public sources into a confidence-marked Obsidian People dossier.
Wide Open Brainstorm
Run multi-model brainstorming for product strategy and experience design.
Second Opinions
Run a bounded independent code review with the opposite-company model first, complete git scope context, and a same-company fallback.
Chezmoi Drift
Check chezmoi dotfiles for drift, unmanaged files, and broken skill links.
Pre Mortem
Run a multi-agent pre-mortem that returns ranked risks and mitigations.