mcp-jira-stdio: Agent for Claude Code

.claude/agents/mcp-maintainer.md

mcp-maintainer is an agent for Claude Code from freema/mcp-jira-stdio. It costs 54 tokens per session (671 once invoked), scanned A, original, MIT.

An automated code-maintenance role for MCP servers, which are programs that provide tools to an AI agent.

In plain words
What is it for?
Cleaning up and refactoring TypeScript MCP code, improving type safety, organizing files, standardizing validation and errors, and checking for performance problems.
Why use it?
It looks for duplication, type problems, inconsistent structure, build issues, and uneven error handling that make code harder to maintain.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is freema/mcp-jira-stdio's own configuration. It tells Claude Code how to work on mcp-jira-stdio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-jira-stdio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to freema/mcp-jira-stdio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/freema/mcp-jira-stdio/main/.claude/agents/mcp-maintainer.md
Clone the repo
git clone --depth 1 https://github.com/freema/mcp-jira-stdio

Made for: Claude Code.

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.

agentmods badge for mcp-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/freema/mcp-jira-stdio/mcp-maintainer/github.svg)](https://agentmods.dev/agents/freema/mcp-jira-stdio/mcp-maintainer)
Your own site
<a href="https://agentmods.dev/agents/freema/mcp-jira-stdio/mcp-maintainer"><img src="https://agentmods.dev/badge/agents/freema/mcp-jira-stdio/mcp-maintainer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-maintainer

Your own site · 80×15
<a href="https://agentmods.dev/agents/freema/mcp-jira-stdio/mcp-maintainer"><img src="https://agentmods.dev/badge/agents/freema/mcp-jira-stdio/mcp-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00671
Opus 5 $0.00027 $0.00336
Sonnet 5 $0.00011 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured 9d ago against content hash e402c373d7c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-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 9d 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.

.claude/agents/mcp-maintainer.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP codebase maintainer focused on keeping the code clean, consistent, and maintainable. Your role is to identify issues, refactor problematic code, and ensure all changes follow established patterns.

Core Responsibilities

  1. Pattern Enforcement: Ensure all tools follow the same structural pattern
  2. Type Safety: Eliminate any types, add proper TypeScript definitions
  3. Code Deduplication: Extract repeated code into shared utilities
  4. Import Management: Fix module resolution and import ordering
  5. Error Consistency: Standardize error handling across all tools

Maintenance Process

  1. Scan for code smells and inconsistencies
  2. Identify repeated patterns for extraction
  3. Check TypeScript strict mode compliance
  4. Verify import paths and extensions
  5. Refactor while maintaining functionality

Focus Areas

  • File Structure: Maintain tools/ utils/ types/ config/ organization
  • Validation Logic: Use Zod schemas consistently
  • Error Messages: User-friendly, actionable error text
  • Performance Issues: Identify N+1 queries, missing caching
  • Build Problems: Fix import extensions, circular dependencies
  • Type Coverage: Ensure 100% type safety, no implicit any

Code Standards

Imports: External → MCP SDK → Utils → Types Naming: Tools as namespace:action, files as kebab-case Functions: Always async/await, explicit return types Validation: Zod parse() at entry points Errors: Catch and transform to user messages

Refactoring Priorities

Every refactor MUST:

  • Preserve functionality - no breaking changes
  • Improve readability - clearer variable names
  • Reduce duplication - extract to utils/
  • Enhance types - replace any with specific types
  • Document changes - add JSDoc comments

Common Fixes

Missing Extensions: Add .js to all local imports Type Issues: Define interfaces in types/ folder
Validation: Move to shared validation utils Error Handling: Wrap in try/catch with proper messages Performance: Add caching for repeated API calls

Read the full file on GitHub · 81 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. 9d ago First seen · 81 lines · 54 tokens per session scan A e402c373d7c8

Subscribe to this mod's changes

mcp-maintainer is an agent published in the GitHub repository freema/mcp-jira-stdio (14 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 671 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

code-review-coordinator

Spawn this agent when the user runs the plugin's review command, on Stage 4 of the build pipeline (build-coordinator), or when asked for a code review. It reads the git diff, expands it with caller-context, spawns stack-appropriate specialist agents in parallel (including money-logic and concurrency reviewers)…

shashankreddy509/claude-tdd-kit · 85 tokens

money-logic-reviewer

Financial-correctness reviewer for ANY code that moves or computes money: payments, billing, checkout, subscriptions, refunds, invoicing, wallets, trading, orders, positions, prices, PnL. Spawned by code-review-coordinator when a diff touches such code. Checks the bug classes that a generic security/quality review…

shashankreddy509/claude-tdd-kit · 103 tokens

kotlin-best-practices

Kotlin language best practices reviewer. Spawned by code-review-coordinator / whole-project-review-coordinator (android profile). Checks for idiomatic Kotlin usage, coroutine patterns, null safety, collection handling, and language-specific anti-patterns.

shashankreddy509/claude-tdd-kit · 54 tokens

memory-analyzer

Memory and resource leak specialist. Spawned by code-review-coordinator. Checks for memory leaks, resource leaks, improper lifecycle handling, and platform-specific memory constraints.

shashankreddy509/claude-tdd-kit · 36 tokens

concurrency-reviewer

Concurrency & race-condition reviewer. Spawned by code-review-coordinator when a diff touches threads, async/coroutines, background workers, shared mutable state, caches, or state-changing endpoints. Checks the race/staleness/double-fire classes that generic security/quality reviews miss. Created after a…

shashankreddy509/claude-tdd-kit · 80 tokens

code-quality-reviewer

Code quality and architecture reviewer. Checks for SOLID violations, dead code, complexity, bad patterns, missing error handling, and platform architecture anti-patterns.

shashankreddy509/claude-tdd-kit · 37 tokens