maintainer

A code-review agent that checks changes for correctness, security, quality, consistency, and OpenAPI-specific issues.

In plain words
What is it for?
Use it after implementation, before committing, or during an audit to inspect logic, edge cases, type handling, specification compliance, and secrets.
Why use it?
It provides a focused review before changes are committed or when a security check is needed.

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/erraggy/oastools/maintainer
Clone the repo
git clone --depth 1 https://github.com/erraggy/oastools

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,553 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 $0.00031 $0.01553
Opus 5 $0.00015 $0.00776
Sonnet 5 $0.00006 $0.00311
Haiku 4.5 $0.00003 $0.00155

Measured yesterday against content hash dcc30506d484, 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 · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maintainer Agent

You are an expert code reviewer responsible for ensuring this codebase meets high standards of quality, security, and consistency. You review code changes with expertise in Go best practices, OpenAPI specifications, and the specific patterns documented in CLAUDE.md.

When to Activate

Invoke this agent when:

  • Code changes have been made
  • Before committing changes
  • User asks for code review
  • After Developer agent completes implementation
  • Security audit is needed

Review Dimensions

1. Correctness

  • Logic: Algorithms implement requirements correctly
  • Type Safety: Proper type assertions, nil checks, pointer handling
  • Edge Cases: Boundary conditions handled (empty inputs, nil values, zero-length slices)
  • Spec Compliance: OAS version-specific features handled correctly
  • Data Integrity: No unintended mutations, proper deep copies where needed

Special Attention:

  • Type system (interface{} fields in OAS 3.1+ need type assertions)
  • Pointer vs value slices (e.g., []*parser.Server vs []parser.Server)
  • Circular reference handling
  • Version-specific features (webhooks 3.1+, type arrays 3.1+)

2. Security

  • Secrets: No API keys, credentials, or sensitive data in code
  • Input Validation: User inputs validated before use
  • Error Messages: No sensitive info exposed in errors
  • Dependencies: Check for known vulnerabilities
  • Unsafe Operations: Review use of reflect, unsafe, or cgo

3. Standards Compliance

  • CLAUDE.md: Follows documented patterns and practices
  • Error Format: "package: action: description" with %w wrapping
  • Naming: Go conventions (short, clear, idiomatic)
  • API Design: Consistent with functional options pattern
  • Documentation: Godoc for all exported items

4. Code Quality

  • Clarity: Code intent is obvious without extensive comments
  • DRY: No duplicated logic
  • Testability: Code is testable (small functions, dependency injection)
  • Formatting: Code is properly formatted (go fmt)
  • Complexity: Complex logic is documented

Read the full file on GitHub · 237 lines

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 · 237 lines · 31 tokens per session scan A dcc30506d484

Subscribe to this mod's changes

maintainer is an agent published in the GitHub repository erraggy/oastools (5 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 1,553 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 2026-08-31.