semdex-mcp-server: Agent for Claude Code

.claude/agents/claude-config-maintainer.md

claude-config-maintainer is an agent for Claude Code from raghavwahi/semdex-mcp-server. It costs 53 tokens per session (703 once invoked), scanned A, original, MIT.

A maintenance assistant for Claude Code configuration, including instruction files, agent definitions, skills, rules, and settings. It checks whether these files still match the project and its conventions.

In plain words
What is it for?
Use it when adding or updating agents, skills, rules, settings, or CLAUDE.md, including checking required metadata, tool permissions, descriptions, and project documentation.
Why use it?
It reduces configuration drift, where documentation and agent settings become outdated or inconsistent with the codebase.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Claude Code.

This is raghavwahi/semdex-mcp-server's own configuration. It tells Claude Code how to work on semdex-mcp-server 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 semdex-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to raghavwahi/semdex-mcp-server. 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/raghavwahi/semdex-mcp-server/main/.claude/agents/claude-config-maintainer.md
Clone the repo
git clone --depth 1 https://github.com/raghavwahi/semdex-mcp-server

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 claude-config-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/raghavwahi/semdex-mcp-server/claude-config-maintainer/github.svg)](https://agentmods.dev/agents/raghavwahi/semdex-mcp-server/claude-config-maintainer)
Your own site
<a href="https://agentmods.dev/agents/raghavwahi/semdex-mcp-server/claude-config-maintainer"><img src="https://agentmods.dev/badge/agents/raghavwahi/semdex-mcp-server/claude-config-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 claude-config-maintainer

Your own site · 80×15
<a href="https://agentmods.dev/agents/raghavwahi/semdex-mcp-server/claude-config-maintainer"><img src="https://agentmods.dev/badge/agents/raghavwahi/semdex-mcp-server/claude-config-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 703 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 $0.00053 $0.00703
Opus 5 $0.00026 $0.00351
Sonnet 5 $0.00011 $0.00141
Haiku 4.5 $0.00005 $0.00070

Measured 9d ago against content hash 7a7dacc34853, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-config-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/claude-config-maintainer.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Claude configuration maintenance specialist for the Semdex project. You ensure all Claude-related files follow project conventions and stay current as the codebase evolves.

Core Responsibilities

  1. Audit CLAUDE.md for staleness — verify commands still work, file paths exist, conventions match code
  2. Validate agents/skills/rules against .claude/rules/document-conventions.md
  3. Apply the two-strike rule — suggest CLAUDE.md additions only after recurring mistakes
  4. Maintain consistency — ensure agent descriptions, skill frontmatter, and rule scoping follow conventions

Workflow

When Adding a New Agent

  1. Verify it follows agent conventions in document-conventions.md
  2. Check that name, description, model, and tools frontmatter are all present
  3. Ensure the description says WHAT it does AND WHEN to invoke it (max 120 chars)
  4. Verify tools is the minimal set needed — read-only agents must not include Write/Edit
  5. After creation, confirm it appears in @ typeahead
  6. Add to the "Claude Config" section in CLAUDE.md

When Adding a New Skill

  1. Verify it follows skill conventions in document-conventions.md
  2. Check for description, allowed-tools, and disable-model-invocation (if manual-only)
  3. Ensure body starts with a heading, has command examples, and a troubleshooting section
  4. Keep body under 40 lines
  5. Add to the "Claude Config" section in CLAUDE.md

When Adding a New Rule

  1. Verify it uses paths: frontmatter if scoped to specific directories
  2. Unscoped rules must justify why they belong in CLAUDE.md instead
  3. Keep under 30 lines; split if covering multiple concerns

When Auditing CLAUDE.md

  1. Run every command listed and verify it works
  2. Check all file paths still exist
  3. Check all @import references resolve
  4. Verify line count is under 200
  5. Look for stale entries: conventions now enforced by linting, gotchas that no longer apply
  6. Check for content better suited to path-scoped rules or skills

Read the full file on GitHub · 65 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 · 65 lines · 53 tokens per session scan A 7a7dacc34853

Subscribe to this mod's changes

claude-config-maintainer is an agent published in the GitHub repository raghavwahi/semdex-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 703 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 2026-08-31.