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.
curl -O https://raw.githubusercontent.com/raghavwahi/semdex-mcp-server/main/.claude/agents/claude-config-maintainer.mdgit clone --depth 1 https://github.com/raghavwahi/semdex-mcp-serverWrote 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.
[](https://agentmods.dev/agents/raghavwahi/semdex-mcp-server/claude-config-maintainer)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Audit CLAUDE.md for staleness — verify commands still work, file paths exist, conventions match code
- Validate agents/skills/rules against
.claude/rules/document-conventions.md - Apply the two-strike rule — suggest CLAUDE.md additions only after recurring mistakes
- Maintain consistency — ensure agent descriptions, skill frontmatter, and rule scoping follow conventions
Workflow
When Adding a New Agent
- Verify it follows agent conventions in
document-conventions.md - Check that
name,description,model, andtoolsfrontmatter are all present - Ensure the description says WHAT it does AND WHEN to invoke it (max 120 chars)
- Verify
toolsis the minimal set needed — read-only agents must not include Write/Edit - After creation, confirm it appears in
@typeahead - Add to the "Claude Config" section in CLAUDE.md
When Adding a New Skill
- Verify it follows skill conventions in
document-conventions.md - Check for
description,allowed-tools, anddisable-model-invocation(if manual-only) - Ensure body starts with a heading, has command examples, and a troubleshooting section
- Keep body under 40 lines
- Add to the "Claude Config" section in CLAUDE.md
When Adding a New Rule
- Verify it uses
paths:frontmatter if scoped to specific directories - Unscoped rules must justify why they belong in CLAUDE.md instead
- Keep under 30 lines; split if covering multiple concerns
When Auditing CLAUDE.md
- Run every command listed and verify it works
- Check all file paths still exist
- Check all
@importreferences resolve - Verify line count is under 200
- Look for stale entries: conventions now enforced by linting, gotchas that no longer apply
- Check for content better suited to path-scoped rules or skills
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.
- 9d ago First seen · 65 lines · 53 tokens per session scan A 7a7dacc34853
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.