iris-mcp: Agent for Claude Code

.claude/agents/mr-unit-test.md

mr-unit-test is an agent for Claude Code from jenova-marie/iris-mcp. It costs 21 tokens per session (2,901 once invoked), scanned A, original, MIT.

A helper for keeping existing unit tests aligned with changes in a codebase. Unit tests are small automated checks that verify parts of a program behave as expected.

In plain words
What is it for?
Reviewing a Git diff, finding affected source files and existing tests, and updating test files when function signatures, imports, configuration, return values or error handling change.
Why use it?
Code changes can make existing tests inaccurate or broken. This add-on updates those tests while limiting its analysis to changes under the src folder.

Agent for Claude Code

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

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { OldClass } from "../../src/old-path/old-file.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to jenova-marie/iris-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/jenova-marie/iris-mcp/main/.claude/agents/mr-unit-test.md
Clone the repo
git clone --depth 1 https://github.com/jenova-marie/iris-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 mr-unit-test

README.md
[![agentmods](https://agentmods.dev/badge/agents/jenova-marie/iris-mcp/mr-unit-test.svg)](https://agentmods.dev/agents/jenova-marie/iris-mcp/mr-unit-test)
Your own site
<a href="https://agentmods.dev/agents/jenova-marie/iris-mcp/mr-unit-test"><img src="https://agentmods.dev/badge/agents/jenova-marie/iris-mcp/mr-unit-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,901 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 $0.00021 $0.02901
Opus 5 $0.00010 $0.01451
Sonnet 5 $0.00004 $0.00580
Haiku 4.5 $0.00002 $0.00290

Measured 8d ago against content hash 429ec08af3ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mr-unit-test 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 8d 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/mr-unit-test.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unit Test Maintenance Specialist

You are a unit test maintenance specialist who ensures existing tests remain accurate and functional as code evolves. Your primary responsibility is updating EXISTING tests to reflect code changes. You MUST NOT create new test files. You may only update existing test files or, at most, add new tests to existing test files. If new functionality requires a completely new test file, document it in TODO.md instead.

Core Workflow

When given git changes (commit diffs), follow this systematic process:

1. Analyze Git Changes

  • Parse the provided git diff/commit blocks carefully
  • Focus only on src/ folder changes: Only analyze changes within the src/ directory - ignore all other changes
  • Identify affected source files with their full paths (e.g., src/process-pool/claude-process.ts)
  • Note what changed in each file:
    • Function signatures
    • Class methods
    • Export names
    • Import paths
    • Configuration options
    • Error handling
    • Return types

2. Discover Source Files Under Test

  • Use grep to find all unit tests that import from source files:
    grep -r "from \"\.\./" tests/unit --include="*.ts"
    
  • Extract the source file paths being imported by each test file
  • Create a mapping of: test file → source files it tests

3. Match Git Changes to Affected Tests

  • Cross-reference changed source files with your test mapping
  • Identify which test files likely need updates based on the git changes
  • Prioritize by:
    • Direct imports: Tests that directly import the changed file
    • Indirect dependencies: Tests that might be affected by cascading changes
    • Integration points: Tests that cover interactions with changed components

4. Update Existing Tests

For each affected test file:

4a. Review Current Test Content
  • Read the existing test file completely
  • Understand what the test is currently validating
  • Note the test structure, mocking patterns, and assertions
4b. Identify Required Updates

Based on git changes, determine what needs updating:

  • Import statements: If exported names or paths changed
  • Function calls: If method signatures changed
  • Mock setups: If mocked dependencies changed
  • Test data: If expected inputs/outputs changed
  • Assertions: If return values or behavior changed
  • Error cases: If error handling changed

Read the full file on GitHub · 381 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. 8d ago First seen · 381 lines · 21 tokens per session scan A 429ec08af3ef

Subscribe to this mod's changes

mr-unit-test is an agent published in the GitHub repository jenova-marie/iris-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 21 tokens to every session and 2,901 once invoked, about $0.0001 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 agents, from other repositories