Agent skill

Maintenance

by platonai in platonai/Browser4

Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra).

Apache-2.0Auto-check passedDevelopment

Install Maintenance

skills CLI
$ npx skills add platonai/Browser4 --skill maintenance -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install platonai/Browser4 maintenance --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/platonai/Browser4.git skills-src && mkdir -p .claude/skills && cp -r skills-src/coworker/skills/maintenance .claude/skills/maintenance && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
maintenance
GitHub stars
1.2k
Token cost
~2.2k tokens
SKILL.md length
643 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
Apache-2.0

At a glance

Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra).

  • Works in 4 steps: Create… → Add a task entry to… → If it's a CI-level check, add it to… → …
  • Asked to run maintenance
  • SKILL.md covers When to Use, How It Works, Usage and Execution Modes, plus 8 more sections
  • Calls pwsh

What it does

Maintenance is an agent skill from platonai/Browser4. Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra). Use when asked to run maintenance, check quality, verify docs, audit SKILLs, or clean up artifacts.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: Browser4 — an AI-native browser engine for autonomous agents, intelligent extraction, and large-scale web automation. The licence is Apache-2.0.

When your agent uses it

  • Asked to run maintenance
  • Clean up artifacts

Example prompts

  • “Use the maintenance skill to orchestrate 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra)”
  • “/maintenance”

Requirements

  • Python 3
  • Docker
  • Pre-approved tools (allowed-tools): Bash(pwsh:*), Bash(./bin/maintenance/*)

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Create bin/maintenance/checks/check-my-thing.ps1 following the result object contract
  2. Add a task entry to bin/maintenance/config.psd1 with Name, Description, Enabled, IntervalSeconds, ScriptPath
  3. If it's a CI-level check, add it to bin/maintenance/ci/invoke-ci-checks.ps1
  4. If it's a nightly check, add it to bin/maintenance/ci/invoke-nightly-checks.ps1

What it can do on your machine

Read from SKILL.md and the folder at commit 0fdba82. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(pwsh:*)
    • Bash(./bin/maintenance/*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pwsh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maintenance loads about 2.2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 643 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from platonai/Browser4 at commit 0fdba82, republished under its Apache-2.0 licence (© platonai). 643 words, ~2,190 tokens.

Download SKILL.mdSave it as .claude/skills/maintenance/SKILL.md (or your agent's skills folder).
name
maintenance
description
Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra). Use when asked to run maintenance, check quality, verify docs, audit SKILLs, or clean up artifacts.
allowed-tools
Bash(pwsh:*), Bash(./bin/maintenance/*)
title
Maintenance — Config-driven quality checks and health monitoring

Maintenance

A config-driven, cross-platform maintenance system that periodically verifies code quality, document correctness, and SKILL documentation AI-friendliness. The orchestrator reads bin/maintenance/config.psd1, runs check scripts on a schedule, persists results to shared state, and reports through multiple formatters (console, JSON, markdown, GitHub annotations).

When to Use

  • "run maintenance"
  • "run CI checks" / "run nightly checks"
  • "check code quality"
  • "verify SKILL frontmatter"
  • "audit documentation links"
  • "check for dead code"
  • "run coverage check"
  • "clean up build artifacts"
  • "add a new maintenance check"
  • "force-run all maintenance tasks"
  • "check the maintenance state"

How It Works

The orchestrator (bin/maintenance/orchestrator.ps1) is the central entry point. It reads task definitions from config.psd1, checks the shared state file to avoid redundant re-runs (unless -Force), executes each task with the configured interval, collects result objects, and routes them through reporters.

Result object contract — every check script emits a PSCustomObject:

powershell
@{
    CheckId    = "A1"
    Name       = "Compilation Check"
    Status     = "passed"  # passed | failed | skipped | error
    DurationMs = 1234
    ExitCode   = 0
    Details    = "Maven + Cargo compile OK"
    Results    = @( @{ Item="..."; Status="passed"; Message="..." } )
    Artifacts  = @( "bin/maintenance/logs/A1-20260714.json" )
    Timestamp  = "2026-07-14T14:30:22Z"
}

Usage

All commands are run from the repository root.

Orchestrator (primary entry point)
bash
# One pass (run pending tasks, skip if still within interval)
pwsh bin/maintenance/orchestrator.ps1 -Once

# Continuous loop (dev mode — warn only, never fails)
pwsh bin/maintenance/orchestrator.ps1

# Force all tasks regardless of last-run state
pwsh bin/maintenance/orchestrator.ps1 -Force -Once

# CI mode (strict — first failure exits 1)
MAINTENANCE_MODE=ci pwsh bin/maintenance/orchestrator.ps1 -Once

# Nightly mode (collects all failures, reports at end)
MAINTENANCE_MODE=nightly pwsh bin/maintenance/orchestrator.ps1 -Once
CI entry points
bash
# Per-commit safety checks (fast)
pwsh bin/maintenance/ci/invoke-ci-checks.ps1

# Full nightly suite (thorough)
pwsh bin/maintenance/ci/invoke-nightly-checks.ps1
Running individual checks
bash
# Syntax-check all PS1 scripts
pwsh bin/maintenance/checks/check-ps1-syntax.ps1

# Validate SKILL.md YAML frontmatter
pwsh bin/maintenance/checks/check-skill-frontmatter.ps1

# Validate internal doc links
pwsh bin/maintenance/checks/check-doc-links-internal.ps1

# Check version consistency across files
pwsh bin/maintenance/checks/check-version-consistency.ps1

# Run code coverage check
pwsh bin/maintenance/checks/check-coverage.ps1

# Detect dead code
pwsh bin/maintenance/checks/check-dead-code.ps1

# Clean stale build artifacts (dry-run first)
pwsh bin/maintenance/checks/clean-build-artifacts.ps1

Execution Modes

ModeBehaviorTrigger
ciStrict: any failure exits 1 immediately. Implies -Force.MAINTENANCE_MODE=ci
nightlyRelaxed: collects all failures, reports at end.MAINTENANCE_MODE=nightly
devWarn only: never fails; all issues are warnings.Default

Check Categories

IDCategoryCountFrequency
ACode Quality & Correctness7CI + Nightly + Weekly
BTest Health4CI + Nightly + Weekly
CDocumentation4CI + Nightly + Hourly
DSKILL Documentation3CI + Nightly + Weekly
EVersion & Release3CI + Nightly + Release
FDependency Management3Nightly + Weekly
GInfrastructure Health3CI + Nightly
HOperational Health3Nightly + Weekly
IAI-Assisted Quality2On-demand + Scheduled

Complete Check Inventory

ScriptCategoryIntervalDescription
check-compilation.ps1A5 minMaven + Cargo compilation
check-fast-tests.ps1B10 minFast JUnit unit tests
check-rust-cli.ps1A1 hrcargo test + cargo clippy
check-doc-links-internal.ps1C1 hrInternal documentation links
check-skill-frontmatter.ps1D1 hrSKILL.md YAML frontmatter
check-version-consistency.ps1E1 hrVersion alignment across files
check-ps1-syntax.ps1A1 hrParse all PS1 for syntax errors
check-dockerfile.ps1G1 hrDocker image builds
check-coverage.ps1B24 hrCode coverage vs thresholds
check-test-tags.ps1B24 hrJUnit test tag taxonomy
check-skill-structure.ps1D24 hrSKILL.md section structure
check-dependency-vulns.ps1F24 hrCVE vulnerability scan
check-maven-deps.ps1F24 hrMaven dependency convergence
check-cargo-audit.ps1F24 hrRust cargo audit
check-doc-links-external.ps1C24 hrExternal URL validation
check-bilingual-readme.ps1C24 hrREADME.md ↔ README.zh.md
check-log-sizes.ps1H24 hrLog directory size audit
check-deprecated-apis.ps1A7 daysDeprecated API usage
check-dead-code.ps1A7 daysDead code and unused imports
check-skill-ai-quality.ps1D7 daysSKILL.md AI quality assessment
check-license-compliance.ps1E7 daysDependency license compatibility
clean-build-artifacts.ps1H7 daysRemove stale build artifacts
clean-temp-files.ps1H7 daysRemove stale temp/lock files

Additional on-demand checks not in the default config: check-changelog-staleness.ps1, check-ci-workflows.ps1, check-e2e-tests.ps1, check-integration-tests.ps1, check-qodana.ps1, check-readme-staleness.ps1, check-release-assets.ps1.

Show full SKILL.md (191 more words)Show less

Shared State

The orchestrator persists run history to bin/maintenance/state/maintenance-state.json, which is tracked in git so the whole team shares one view.

How skip logic works: A task is skipped if it ran within its configured IntervalSeconds. This means CI nightly running check-coverage prevents a developer's orchestrator from re-running it within 24 hours. Force mode (-Force) or CI mode bypass this entirely.

File locking prevents corruption when two processes write simultaneously. Stale locks (older than 60 seconds) are automatically broken.

Thresholds

All numeric thresholds live in bin/maintenance/thresholds/thresholds.psd1. Override any value via environment variable:

bash
MAINTENANCE_Coverage_Global=0.75 pwsh bin/maintenance/orchestrator.ps1 -Once
MAINTENANCE_LogHealth_MaxTotalMB=200 pwsh bin/maintenance/orchestrator.ps1 -Once

Adding a New Check

  1. Create bin/maintenance/checks/check-my-thing.ps1 following the result object contract
  2. Add a task entry to bin/maintenance/config.psd1 with Name, Description, Enabled, IntervalSeconds, ScriptPath
  3. If it's a CI-level check, add it to bin/maintenance/ci/invoke-ci-checks.ps1
  4. If it's a nightly check, add it to bin/maintenance/ci/invoke-nightly-checks.ps1

Reporters

ScriptOutput
reporters/report-console.ps1Colorized terminal output
reporters/report-json.ps1JSON files under logs/
reporters/report-github-annotations.ps1CI workflow commands
reporters/report-summary.ps1Markdown summary

Directory Layout

bin/maintenance/
├── config.psd1              # Task definitions and intervals
├── orchestrator.ps1         # Master scheduler
├── common/
│   ├── MaintenanceUtil.ps1  # Logging, results, threshold helpers
│   └── MaintenanceState.ps1 # State I/O with file locking
├── checks/                  # 30 check/clean scripts
├── reporters/               # Output formatters
├── ci/                      # CI entry points
├── state/
│   └── maintenance-state.json  # Shared run history (git-tracked)
└── thresholds/
    └── thresholds.psd1      # Numeric thresholds

Dependencies

  • PowerShell Core 6+ (pwsh)
  • Git (repository root resolution)
  • Maven Wrapper (mvnw / mvnw.cmd)
  • Cargo (Rust CLI checks)
  • Docker (Qodana, integration tests, Dockerfile checks)
  • Python 3 (bin/quality/fix-links.py)
  • ripgrep (rg) recommended for fast content search

© platonai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in coworker/skills/maintenance of platonai/Browser4.

Open the folder on GitHubat commit 0fdba82

Compare with similar skills

Maintenance next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Maintenance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Maintenance this skillplatonai/Browser41.2k—~2.2kAutomated safety check: PassApache-2.0
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from platonai/Browser4

All 17 skills in this repo
  • Data Validation

    platonai/Browser4

    Validates data against common and custom rules (required fields, formats, ranges).

    1.2k GitHub stars~896 tokensUpdated yesterday
    Auto-check passed
  • Form Filling

    platonai/Browser4

    Automatically fills web forms using provided field data and can optionally submit the form.

    1.2k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Web Scraping

    platonai/Browser4

    Extracts data from web pages using browser automation and CSS/JavaScript selectors.

    1.2k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Organize Task Files

    platonai/Browser4

    Lists, pairs, deduplicates, and moves task files across the Coworker task state machine (0draft → 6git-pushed).

    1.2k GitHub stars~801 tokensUpdated yesterday
    Auto-check passed
  • Task Token Usage

    platonai/Browser4

    Analyzes Claude Code session traces (JSONL) and draft task files to report token usage per task.

    1.2k GitHub stars~701 tokensUpdated yesterday
    Auto-check passed
  • Weather

    platonai/Browser4

    Fetches current weather conditions and a 7-day forecast for a requested location using Open-Meteo geocoding and forecast APIs.

    1.2k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Maintenance

What does Maintenance do?

Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra). Maintenance is an agent skill from platonai/Browser4. Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra).

When should I use Maintenance?

Maintenance fits situations like: asked to run maintenance; clean up artifacts.

How do I install Maintenance in Claude Code?

Run `npx skills add platonai/Browser4 --skill maintenance -a claude-code`. Or copy the skill folder (coworker/skills/maintenance in platonai/Browser4) into .claude/skills/maintenance in your project. Claude Code loads it when a task matches its description.

How do I install Maintenance in Codex?

Run `npx skills add platonai/Browser4 --skill maintenance -a codex`. Or copy the skill folder (coworker/skills/maintenance in platonai/Browser4) into .agents/skills/maintenance in your project. Codex loads it when a task matches its description.

Can I use Maintenance in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add platonai/Browser4 --skill maintenance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maintenance, .gemini/skills/maintenance, .github/skills/maintenance and .opencode/skills/maintenance in your project.

What does Maintenance need to run?

Going by SKILL.md and its folder, Maintenance needs the command-line tools its instructions call (pwsh). Our summary lists: Python 3; Docker. Its frontmatter pre-approves these tools: Bash(pwsh:*), Bash(./bin/maintenance/*).

Does Maintenance access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Maintenance safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Maintenance use?

Maintenance is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Maintenance use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Maintenance?

Skills that share tags, products or a category with Maintenance: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Maintenance?

platonai (a GitHub user) maintains it in platonai/Browser4, which has 1,152 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 7, 2026.

Source: platonai/Browser4 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.