night-watch
Pre-flight for leaving agents running unattended: pin the done predicate, the wake mechanism, the verifier, the budgets, the trail, and the escalation gates…
Skill by peterpme
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/peterpme-night-watch
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/night-watch
What's inside
- Skill name
night-watch- Description
- Pre-flight for leaving agents running unattended: pin the done predicate, the wake mechanism, the verifier, the budgets, the trail, and the escalation gates, then hand off to the matching long-run playbook. Use for /night-watch, 'set up an overnight run', 'I'm going to bed, set this up', 'run this while I'm away', or before any autonomous run, autopilot, or orchestrate program.
- License
- unknown
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from peterpme/dotfiles
- 0.628score
effect-v4-best-practices
peterpme
Effect v4 best practices for TypeScript.
SkillBFreshness: B★ 93Claude Code +9 - 0.628score
debugger
peterpme
Session problem log for improving ppstack.
SkillBFreshness: B★ 93Claude Code +9 - 0.628score
peer-review
peterpme
Send one neutral review brief to reviewers from other model families (Claude Fable 5.1, Codex on Sol, Grok 4.6) and compare their answers.
SkillBFreshness: B★ 93Claude Code +9 - 0.626score
petey
peterpme
Peter's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillBFreshness: B★ 93Claude Code +9 - 0.625score
proof-plan
peterpme
Write the proof before the code: turn a brief or feature request into the checks that will show it works on the real surface, with the evidence each check…
SkillBFreshness: B★ 93Claude Code +9 - 0.625score
herdr
peterpme
Peter's Herdr conventions.
SkillBFreshness: B★ 93Claude Code +9 - 0.625score
no-comments
peterpme
Spawn Comment Sicko, remove rejected comments, fix accepted structural findings, and offer encodings for valid constraints.
SkillBFreshness: B★ 93Claude Code +9 - 0.625score
no-stupid-tests
peterpme
Spawn Test Butcher on the scoped test files, trim tests that are not worth keeping, then write the real tests it flags as missing.
SkillBFreshness: B★ 93Claude Code +9 - 0.624score
cloudflare-setup
peterpme
Use when creating a new worker or wrangler file.
SkillBFreshness: B★ 93Claude Code +9 - 0.621score
grill
peterpme
Interview the user round by round until a plan, feature, or idea has no silently assumed branch left, then hand back a design brief with a done predicate.
SkillBFreshness: B★ 93Claude Code +9 - 0.608score
architect
peterpme
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillBFreshness: B★ 93Claude Code +9 - 0.605score
create-verification-skill
peterpme
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillBFreshness: B★ 93Claude Code +9
Signals
- Stars
- 93
- Forks
- 13
- Open issues
- 0
- Last commit (this folder)
- Sep 3, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/peterpme/dotfiles
- Website
- github.com/peterpme/dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from peterpme
- 0.628score
peer-review
peterpme
Send one neutral review brief to reviewers from other model families (Claude Fable 5.1, Codex on Sol, Grok 4.6) and compare their answers.
SkillBFreshness: B★ 93Claude Code +9 - 0.628score
debugger
peterpme
Session problem log for improving ppstack.
SkillBFreshness: B★ 93Claude Code +9 - 0.628score
effect-v4-best-practices
peterpme
Effect v4 best practices for TypeScript.
SkillBFreshness: B★ 93Claude Code +9 - 0.626score
petey
peterpme
Peter's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillBFreshness: B★ 93Claude Code +9 - 0.625score
herdr
peterpme
Peter's Herdr conventions.
SkillBFreshness: B★ 93Claude Code +9 - 0.625score
no-stupid-tests
peterpme
Spawn Test Butcher on the scoped test files, trim tests that are not worth keeping, then write the real tests it flags as missing.
SkillBFreshness: B★ 93Claude Code +9
Cite this page
night-watch skill. Agent Mart. https://agentmart.dev/skills/peterpme-night-watch (last updated 2026-10-24)