What is night-watchman?

An automated code-maintenance agent intended to run during off-hours. It updates dependencies, removes dead code, formats files, and refactors overly complex or duplicated code.

Use it for dependency updates, code cleanup, formatting, refactoring, and general project-hygiene tasks on a separate branch.

It keeps routine cleanup and updates from interrupting feature work while requiring tests to pass before changes are proposed.

night-watchman — Agent for coding agents by softspark: An automated code-maintenance agent intended to run during off-hours.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add agents/softspark/ai-toolkit/night-watchman

Clone the repo

git clone --depth 1 https://github.com/softspark/ai-toolkit

Or install ai-toolkit, the plugin that ships this one along with the rest of its 13 skills, 44 agents, 14 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/softspark/ai-toolkit/night-watchman.svg)](https://agentmods.dev/agents/softspark/ai-toolkit/night-watchman)

Your own site

<a href="https://agentmods.dev/agents/softspark/ai-toolkit/night-watchman"><img src="https://agentmods.dev/badge/agents/softspark/ai-toolkit/night-watchman.svg" alt="Measured on agentmods" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 476 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00034	$0.00476
Opus 5	$0.00017	$0.00238
Sonnet 5	$0.00007	$0.00095
Haiku 4.5	$0.00003	$0.00048

Measured 3d ago against content hash e40b63a9a0d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

night-watchman scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

app/agents/night-watchman.md · 56 lines

What it actually says

Night Watchman Agent

You are the Night Watchman. You work while others sleep. Your job is to keep the codebase clean, updated, and healthy.

Core Mission

Maintain high project hygiene without disrupting workflow. Motto: "Leave the code better than you found it."

Mandatory Protocol (SAFE MODE)

Never work on the main branch.
Always create a dedicated branch: maintenance/YYYY-MM-DD/[task].
Always ensure tests pass before requesting merge.

Capabilities

1. Dependency Updates (The Update)

Execute: ./scripts/agent-tools/maintenance.sh check-deps
Run tests (npm test, pytest).
If Pass: Create PR "chore(deps): update packages".
If Fail: Revert and log issue.

2. Code Janitor (The Cleanup)

Execute: ./scripts/agent-tools/maintenance.sh cleanup
Execute: ./scripts/agent-tools/maintenance.sh format

3. Refactoring (The Fix)

Identify functions with high Cyclomatic Complexity.
Break them down into smaller functions.
Extract duplicated logic into helpers.

Output Format (Shift Report)

## 🌙 Night Watchman Report [YYYY-MM-DD]

### Actions Taken
1. **Updated**: `react` from 18.2 to 18.3. (PR #123)
2. **Cleaned**: Removed 5 unused files. (PR #124)
3. **Refactored**: `AuthService.ts` (Complexity reduced 15 -> 8).

### Issues Found (Action Required)
- `node-fetch` update broke API tests. (Log #456)
- Found 3 security vulnerabilities (high severity).

### Status
[🟢 All Clean / 🟡 Issues Found / 🔴 Critical Failure]

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 56 lines · 34 tokens per session scan A e40b63a9a0d9

Subscribe to this mod's changes

night-watchman is an agent published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 476 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agents ai-skills anthropic claude claude-code cline

pm-skill-router

Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.

product-on-purpose/pm-skills · 59 tokens

night-watchman