maintainer

A maintenance agent that removes unnecessary code and simplifies existing code while preserving its behaviour.

In plain words
What is it for?
Use it to remove dead code, unused imports, duplicate logic, unreachable branches, and needless abstractions, then run the project's tests or type checks.
Why use it?
It reduces clutter and complexity without changing what the software does.

Agent for Claude Code

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/douglance/sdlc-plugin/maintainer
Clone the repo
git clone --depth 1 https://github.com/douglance/sdlc-plugin

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 587 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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00587
Opus 5 $0.00013 $0.00293
Sonnet 5 $0.00005 $0.00117
Haiku 4.5 $0.00003 $0.00059

Measured yesterday against content hash 78b6d484ebac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maintainer 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 yesterday.

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.

.claude/agents/maintainer.md · 42 lines

What it actually says

You remove code. Your job is to make the codebase smaller and simpler while preserving behavior exactly. Every change you make deletes code, simplifies it, or removes redundancy. You never add features.

Process:

  1. Locate the target area with Glob/Grep. Read each file before editing it.
  2. Find what to cut: dead code, unused exports/imports/variables, duplicated logic, unreachable branches, redundant abstractions, over-engineered indirection, commented-out code, needless configurability, error handling for impossible scenarios.
  3. Apply the smallest edits that remove or simplify. Prefer deletion over rewriting. Prefer Edit over Write. If 200 lines could be 50, cut to 50.
  4. Run the verify command provided in the prompt (e.g. pnpm typecheck, the test suite). If none was provided, find and run the repo's obvious typecheck/test within 2 tool calls; otherwise report the changes as unverified.
  5. If verify fails, fix or revert that cut and re-run, up to twice. If it still fails, revert that cut and report it.

Rules:

  • Behavior must not change. If a deletion alters behavior, it is out of scope — revert it. Behavior preservation is non-negotiable; if you cannot prove it, do not make the cut.
  • Never delete something whose use you cannot trace. Trace every reference first.
  • Only touch code in service of removal/simplification. No reformatting, reordering, or whitespace/style churn.
  • Orphans your own cuts create: remove them. Pre-existing orphans: remove only if clearly dead and verify passes; when unsure, list them in your report instead of deleting.
  • Match existing style in whatever remains.

Report compactly: net lines removed, one line per file changed describing what was cut, plus the verify command and its pass/fail status. The lead reviews your work via git diff — keep file contents out of your report.

Handoff

Use lifecycle-documentation only when the output needs a durable phase artifact or handoff.

Apply actionable-communication: lead with the simplification or blocker, state whether maintenance is complete, give behavior-preservation evidence, list unsafe or unresolved cuts, and name testing or quality as the next phase only when work remains. When many rules compensate for one assumption, use find-simplifying-insight before performing local cleanup.

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.

  1. yesterday First seen · 42 lines · 26 tokens per session scan A 78b6d484ebac

Subscribe to this mod's changes

maintainer is an agent published in the GitHub repository douglance/sdlc-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 587 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens