ibu-mcp: Skill for Claude Code

.claude/skills/add-ibu-tool/SKILL.md

add-ibu-tool is a skill for Claude Code from Haris0059/ibu-mcp. It costs 41 tokens per session (591 once invoked), scanned A, original, MIT.

A guide for adding a new tool to the IBU MCP server, which connects the coding agent to IBU's REST API.

In plain words
What is it for?
It helps developers add, expose, or wrap an IBU REST endpoint as a callable agent tool.
Why use it?
It provides the expected file locations, naming style, input definitions, and request-handling pattern, reducing guesswork when exposing an API endpoint.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Haris0059/ibu-mcp's own configuration. It tells Claude Code how to work on ibu-mcp 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 ibu-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Haris0059/ibu-mcp. 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/Haris0059/ibu-mcp/main/.claude/skills/add-ibu-tool/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Haris0059/ibu-mcp

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 add-ibu-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/haris0059/ibu-mcp/add-ibu-tool/github.svg)](https://agentmods.dev/skills/haris0059/ibu-mcp/add-ibu-tool)
Your own site
<a href="https://agentmods.dev/skills/haris0059/ibu-mcp/add-ibu-tool"><img src="https://agentmods.dev/badge/skills/haris0059/ibu-mcp/add-ibu-tool/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 add-ibu-tool

Your own site · 80×15
<a href="https://agentmods.dev/skills/haris0059/ibu-mcp/add-ibu-tool"><img src="https://agentmods.dev/badge/skills/haris0059/ibu-mcp/add-ibu-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 591 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 $0.00041 $0.00591
Opus 5 $0.00020 $0.00296
Sonnet 5 $0.00008 $0.00118
Haiku 4.5 $0.00004 $0.00059

Measured 11d ago against content hash 23fef752e118, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

add-ibu-tool 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 11d 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/skills/add-ibu-tool/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding a new IBU MCP tool

Follow these steps to add a tool. Match the patterns already in src/tools/*.ts rather than inventing new ones.

1. Pick the domain file

Existing files in src/tools/: student.ts, grades.ts, attendance.ts, notifications.ts, finances.ts, activities.ts. If the new tool fits one of these domains, append to its exported array. Only create a new file for a genuinely new domain.

2. Name the tool

Use the ibu_<verb>_<noun> convention (e.g. ibu_get_transcript, ibu_mark_notification_read). The name is what shows up to Claude — make it specific and discoverable.

3. Define the entry

Each tool is an object in the domain array with this shape:

{
  name: "ibu_get_something",
  description: "One sentence describing what it returns and when to use it.",
  inputSchema: {
    type: "object",
    properties: {
      // string params; use `enum` for fixed sets; add `description` for each
      academicYearId: { type: "string", description: "Academic year ID from ibu_get_academic_years." },
    },
    required: [],
  },
  handler: async (input: { academicYearId?: string }) => {
    const data = await ibufetch(`some/path${input.academicYearId ? `?yearId=${input.academicYearId}` : ""}`);
    return JSON.stringify(data, null, 2);
  },
}

The registrar in src/index.ts converts inputSchema.properties into zod — it currently handles string/enum only. If the new tool needs a non-string param, extend the registrar accordingly.

4. Register

If you added to an existing file, no registration change is needed (the array is already imported in src/index.ts). If you created a new file, import its array in src/index.ts and add a registerTools(...) call alongside the others.

5. Verify

Run npm run build. The TS config is strict — fix any errors before reporting done. Do not add console.log to stdout (it breaks the stdio MCP channel — use console.error if you need debug output).

6. Error handling

Let ibufetch() raise. It already maps 401/402/403/301/500 to user-facing messages. Don't wrap the call in try/catch unless you have a tool-specific recovery path.

Read the full file on GitHub · 54 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. 11d ago First seen · 54 lines · 41 tokens per session scan A 23fef752e118

Subscribe to this mod's changes

add-ibu-tool is a skill published in the GitHub repository Haris0059/ibu-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 591 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.

Related

Other skills, from other repositories

cloudkit-sync

Generate CloudKit sync infrastructure using CKSyncEngine with conflict resolution, sharing, and account monitoring. Use when adding iCloud sync to an iOS/macOS app.

rshankras/claude-code-apple-skills · 37 tokens

offline-queue

Generates an offline operation queue with persistence, automatic retry on connectivity, and conflict resolution. Use when user needs offline-first behavior, queued mutations, or pending operations that sync when back online.

rshankras/claude-code-apple-skills · 42 tokens

push-notifications

Generate push notification infrastructure with APNs registration, handling, and rich notifications. Use when adding push notifications, configuring APNs, notification categories/actions, or rich notifications with images and custom UI.

rshankras/claude-code-apple-skills · 42 tokens

http-cache

Generates an HTTP caching layer with Cache-Control parsing, ETag/conditional requests, and offline fallback. Use when user wants to add response caching, offline support, or reduce API calls.

rshankras/claude-code-apple-skills · 41 tokens

pagination

Generates pagination infrastructure with offset or cursor-based patterns, infinite scroll, and search support. Use when user wants to add paginated lists, infinite scrolling, or load-more functionality.

rshankras/claude-code-apple-skills · 38 tokens

networking-layer

Generates a protocol-based networking layer with async/await, error handling, and swappable implementations. Use when user wants to add API client, networking, or HTTP layer.

rshankras/claude-code-apple-skills · 39 tokens