What makes Night Shift notable?

1K downloads. Trust evidence available

How should Night Shift be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Night Shift

Queue coding plans during the day, approve them, execute later in isolated worktrees, and inspect reports. Background agentic execution requires an explicitl... Skill: Night Shift Owner: vardhineediganesh877-ui Summary: Queue coding plans during the day, approve them, execute later in isolated worktrees, and inspect reports. Background agentic execution requires an explicitl... Tags: latest:1.0.5 Version history: v1.0.5 | 2026-04-26T23:02:23.913Z | user Registry package hardening: exclude local ops watchdog/notification/test helpers from public package, keep core executor/pr

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.5release · observed Apr 26, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s174de6375a63p24r7c7yf857n85j8e3:night-shift

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-vardhineediganesh877-ui-night-shift/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

148,469 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: night-shift
version: 1.0.5
description: "Queue coding plans during the day, approve them, execute later in isolated worktrees, and inspect reports. Background agentic execution requires an explicitly configured non-interactive runner."
metadata:
  {
    "openclaw":
      {
        "requires": { "bins": ["python3", "git"] },
        "optional":
          {
            "bins": ["agent", "cursor", "claude"],
            "env":
              [
                "OPENCLAW_WORKSPACE",
                "NIGHT_SHIFT_DATA_DIR",
                "NIGHT_SHIFT_MODEL",
                "CURSOR_CLI",
                "CURSOR_API_KEY",
                "TELEGRAM_BOT_TOKEN",
                "TELEGRAM_CHAT_ID",
                "NIGHT_SHIFT_CHAT_ID",
              ],
          },
        "capabilities":
          [
            "filesystem-read-write",
            "git-worktrees",
            "subprocess-execution",
            "optional-cursor-cli",
            "optional-claude-cli",
            "optional-telegram-notifications",
            "optional-model-provider-calls",
          ],
      },
  }
---

# Night Shift

Night Shift is an autonomous queued-execution skill for engineering work.

Instead of asking the agent to do one large coding task immediately, you build a queue of plans, review or approve them, then run them in a controlled batch window. Each plan is split into phases, executed in isolation, verified, checkpointed, and summarized in a report.

**Mental model:**
- Daytime: create and refine plans
- Before execution: approve what is safe to run
- Execution window: Night Shift runs plans phase by phase
- Morning: inspect results, merge, retry, or continue

This is useful when you want:
- deferred execution instead of immediate chat-time work
- safer batching for multi-step changes
- isolated worktrees per plan
- retry and checkpoint behavior
- a written report after execution

---

## When to Use

Use Night Shift when the user asks for things like:
- “good night”
- “queue this for later”
- “plan add …”
- “run these approved plans overnight”
- “night shift status”
- “show my morning report”
- “retry plan #3”
- “merge that finished plan”

Prefer Night Shift over immediate execution when:
- the work is multi-phase
- the task needs isolation from the main repo state
- the user wants review/approval before execution
- the work may take a long time
- you want a queue of tasks rather than one interactive run

Do **not** use Night Shift for:
- tiny one-off edits better handled immediately
- high-risk production actions without review
- tasks that require constant human decisions mid-run
- public/external actions that should be explicitly approved in the moment

---

## Core Concepts

### 1. Plan
A plan is the unit of queued work. It includes:
- title
- optional description
- optional repo URL
- priority
- token/time budget hints
- generated phases
- status and execution metadata

### 2. Phase
Each plan is split into phases. A phase has:
- a title
- a prom

_meta.json

{
  "ownerId": "kn7380dt93q0wx6x1zx5b4y8z985kjww",
  "slug": "night-shift",
  "version": "1.0.5",
  "publishedAt": 1777244543913
}

INSTALL.md

# Night Shift Install and Setup

## Install from ClawHub

```bash
openclaw skills install vardhineediganesh877-ui/night-shift
```

## Verify local requirements

```bash
cd ~/.openclaw/workspace
python3 skills/night-shift/scripts/preflight.py --json
```

Required dependencies are `python3` and `git`. Cursor/Claude runners are optional, but any queued phase that uses them requires those CLIs to work non-interactively.

## Recommended first run: disposable workspace

```bash
export OPENCLAW_WORKSPACE=/tmp/night-shift-demo
mkdir -p "$OPENCLAW_WORKSPACE"
python3 ~/.openclaw/workspace/skills/night-shift/scripts/preflight.py --json
python3 ~/.openclaw/workspace/skills/night-shift/scripts/executor.py dry-run
```

Dry-run should write a preview report only. It should not mark plans complete or create success checkpoints.

## Background/systemd setup

Detached timers need explicit environment. Create a private env file if needed:

```bash
cp skills/night-shift/.night-shift.env.example ~/.openclaw/workspace/.night-shift.env
chmod 600 ~/.openclaw/workspace/.night-shift.env
```

Then edit values for your environment. Do not commit real secrets.

Before enabling a timer, run preflight in the same user context that will run the service.

REFERENCE.md

# Night Shift Reference

This file is the operational reference for the Night Shift skill.

It complements `SKILL.md` by focusing on setup, runtime expectations, file layout, and practical caveats.

---

## 1. What Night Shift Actually Is

Night Shift is a queued autonomous execution framework for coding work.

It is **not** just a prompt pattern. It includes:
- plan storage
- phase generation
- isolated worktrees
- execution routing
- verification
- checkpointing
- reporting
- monitoring helpers

Think of it as a lightweight unattended engineering operator.

---

## 2. Minimum Runtime Expectations

Night Shift expects a host environment with:
- Python 3
- git
- a writable workspace
- permission to create directories/files under `data/night-shift/`
- a repo or project context where worktrees and diffs make sense

If those are missing, the skill may still partially function, but the core value drops sharply.

---

## 3. Security Review Notes

Night Shift is powerful by design. It can run shell commands, create git worktrees, call coding CLIs, and write reports/checkpoints. That means automated registries may classify it as suspicious even when the package is behaving as intended.

Expected capabilities:
- local file and directory writes under the configured workspace
- git worktree / diff / commit / reset operations
- subprocess execution for approved phase methods
- optional calls to host-provided tools such as Cursor CLI, Claude Code, or subagents
- optional Telegram notifications when notification environment variables are configured

Not expected:
- bundled secrets or private tokens
- cryptocurrency mining
- hidden persistence outside the configured workspace
- unsolicited external network calls beyond host-configured tools/notifications
- production deployment unless a user-approved phase explicitly performs it

SECURITY.md

# Night Shift Security Model

Night Shift is a powerful queued execution framework. Treat it like a coding agent runner, not a passive note-taking skill.

## What Night Shift can do

When you approve and run plans, Night Shift may:

- read and write files inside the configured workspace
- create git branches and worktrees under `data/night-shift/worktrees/`
- run subprocesses for shell phases and verification commands
- call optional coding runners such as Cursor CLI (`agent`/`cursor`) or Claude Code (`claude`)
- run tests, linters, build commands, and smoke checks
- write checkpoints, reports, logs, and failure-memory records
- optionally send Telegram notifications if notification tokens are configured

## What Night Shift should not do by default

Night Shift should not:

- run against production repositories without review
- execute unreviewed public/external actions
- send notifications unless recipients and tokens are explicitly configured
- mark dry-runs as completed live work
- continue through every plan after a shared runner/preflight failure

## Required runtime dependencies

Required:

- `python3` 3.11+
- `git`
- writable workspace/data directory

Optional, depending on phase execution methods:

- Cursor CLI: `agent` or `cursor`
- Claude Code CLI: `claude`
- Telegram notification env vars

## Environment variables

Optional variables read by the skill:

- `OPENCLAW_WORKSPACE` — workspace root; defaults to the OpenClaw workspace that contains this skill
- `NIGHT_SHIFT_DATA_DIR` — Night Shift state directory; defaults to `$OPENCLAW_WORKSPACE/data/night-shift`
- `NIGHT_SHIFT_MODEL` — model hint for compatible runners
- `CURSOR_CLI` — explicit path to Cursor/agent CLI
- `CURSOR_API_KEY` — optional non-interactive Cursor auth, if supported by your CLI setup
- `TELEGRAM_BOT_TOKEN`, `TELEGRAM_CHAT_ID`, `NIGHT_SHIFT_CHAT_ID` — optional notifications

Never commit real tokens. Use a local env file such as `.night-shift.env` and keep it out of published packages.

## Safe first run

Use an isolated disposable workspace first:

```bash
export OPENCLAW_WORKSPACE=/tmp/night-shift-demo
python3 skills/night-shift/scripts/preflight.py --json
python3 skills/night-shift/scripts/executor.py dry-run
```

Dry-run is intended to be read-only. It should produce a preview report and must not mark plans complete or write success checkpoints.

## Background runner warning

Detached systemd/timer execution does not automatically inherit your interactive shell environment. Before live unattended execution, run preflight in the same user/service context. In particular, Cursor CLI phases need `HOME`, `PATH`, and a non-interactive auth strategy.

If preflight says Cursor/Claude is not ready, fix the environment or change the queued phases before running live execution.

## Verification command policy

Verification commands can execute subprocesses in the worktree. Prefer explicit, narrow commands such as:

- `python3 -m pytest`
- `npm test`
- `npm run lint`
- `ruff

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.