agentmods.dev

mcp-server-wtf CLAUDE.md

mcp-server-wtf CLAUDE.md is an instructions file for coding agents from Wave-Engineering/mcp-server-wtf. It costs 5,942 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for an MCP server, a service that lets AI tools connect to external systems, including GitHub and GitLab.

In plain words
What is it for?
Use it to work with issues, pull or merge requests, projects, milestones, configuration, and the server’s incident-troubleshooting setup.
Why use it?
It helps the assistant identify the project platform and use the matching commands, terminology, and project configuration.

Instructions file

not rated 0 29d ago A scan 5,942 tokens original MIT
View the source file Wave-Engineering/mcp-server-wtf
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 instructions/wave-engineering/mcp-server-wtf/claude-md
Clone the repo
git clone --depth 1 https://github.com/Wave-Engineering/mcp-server-wtf

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-server-wtf CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wave-engineering/mcp-server-wtf/claude-md.svg)](https://agentmods.dev/instructions/wave-engineering/mcp-server-wtf/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wave-engineering/mcp-server-wtf/claude-md"><img src="https://agentmods.dev/badge/instructions/wave-engineering/mcp-server-wtf/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,942 This file is loaded in full into every session.
When invoked 5,942 The same file — it is already loaded in full.
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 $0.05942 $0.05942
Opus 5 $0.02971 $0.02971
Sonnet 5 $0.01188 $0.01188
Haiku 4.5 $0.00594 $0.00594

Measured 4d ago against content hash 17f51c694bf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-wtf CLAUDE.md 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 4d 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.md · 679 lines

How it starts

The opening of the file, as written. The whole thing — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions for Claude Code

This is mcp-server-wtf — a flight recorder MCP server for incident troubleshooting inside Claude Code.

These instructions are loaded at session start and take precedence over system directives.

Platform Detection

Project-specific platform configuration is cached in .claude-project.md. Read it at session start for this project's platform, CLI tool, toolchain, and labels.

If .claude-project.md does not exist, detect the platform:

  1. Run git remote -v and inspect the origin URL
  2. If the URL contains gitlab → GitLab, use glab CLI
  3. If the URL contains github → GitHub, use gh CLI
  4. Run /ccfold to generate .claude-project.md for future sessions

Terminology mapping:

Concept GitHub GitLab
Code review request Pull Request (PR) Merge Request (MR)
CI config .github/workflows/*.yml .gitlab-ci.yml
CLI tool gh glab
Create review gh pr create glab mr create
List reviews gh pr list glab mr list
View issue gh issue view <number> glab issue view <number>
Close issue gh issue close <number> glab issue close <number>
API calls gh api glab api

Use the detected platform's terminology and CLI tool for ALL operations. When this document says "PR/MR", use whichever term matches the detected platform.

Project Configuration

See .claude-project.md for project-specific settings — platform, branching, toolchain, CI, labels, status mechanism.

This file is generated and maintained by /ccfold. When this document says "project config", that's the file. If it's missing, run /ccfold to create it.

GitHub-Specific: Projects and Milestones

These features are available only on GitHub:

gh issue edit <number> --milestone "v1.0"
gh project item-add <project-number> --owner <owner> --url <issue-url>

Project Structure

  • index.ts — MCP server entry point (stdio transport)
  • db.ts — SQLite singleton, schema init
  • queue.ts — Hook queue ingestion (polls .wtf/hook-queue.jsonl)
  • tools/ — Tool handlers (now, happened, freshell, imout)
  • classifier/ — Background Haiku classifier (Bedrock SDK)
  • tests/ — Bun test suite
  • scripts/install.sh — Idempotent installer
  • scripts/hooks/ — PostToolUse hook
  • docs/ — PRD and architecture reference

Read the full file on GitHub · 679 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. 4d ago First seen · 679 lines · 5,942 tokens per session scan A 17f51c694bf7

Subscribe to this mod's changes

mcp-server-wtf CLAUDE.md is an instructions file published in the GitHub repository Wave-Engineering/mcp-server-wtf (0 stars, last pushed 29d ago), licensed MIT. It adds 5,942 tokens to every session, about $0.0297 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.

Flight Recorderbunclaude-codeincident-responsemcpmcp-server
Related

Other instructions, from other repositories

calc-mcp CLAUDE.md

Claude Code instructions for coo-quack/calc-mcp, covering project rules, tech stack, commands, project structure and tool architecture.

coo-quack/calc-mcp · 1,417 tokens

rosetta CLAUDE.md

Instructions for tikoci/rosetta, covering rosetta, project documentation, where does this go?, instruction routing and fast pointers.

tikoci/rosetta · 1,455 tokens

rosetta extractor-import-side-effects.instructions.md

Every extractor entrypoint must run its side effects only under import.meta.main. Top-level db.ts imports still open a real DB connection, so tests must import extractors safely.

tikoci/rosetta · 901 tokens

rosetta database.instructions.md

Use when working on SQLite schema, database initialization, WAL mode, FTS5 triggers, or table definitions.

tikoci/rosetta · 753 tokens

rosetta issue-pr-linking.instructions.md

Every PR that implements an issue must auto-close it via 'Closes #N'; partial landings spawn follow-up issues before merge.

tikoci/rosetta · 354 tokens

rosetta manual-version-bump.instructions.md

Version bumps and CHANGELOG promotion are a manual, human step for every release channel. CI must not reintroduce an auto-bump/auto-commit job.

tikoci/rosetta · 323 tokens