froggo-mission-control: Agent for Claude Code

.claude/agents/colosseum-tester.md

colosseum-tester is an agent for Claude Code from ProfFroggo/froggo-mission-control. It costs 49 tokens per session (737 once invoked), scanned A, original, Apache-2.0.

Unit test specialist for the Colosseum monorepo. Writes Vitest tests using the makeMockRepo pattern, covering happy paths, not-found, empty collections, date serialization, side effects, and authorization checks.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the TodoWrite tool.

This is ProfFroggo/froggo-mission-control's own configuration. It tells Claude Code how to work on froggo-mission-control 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 froggo-mission-control configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ProfFroggo/froggo-mission-control. 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/ProfFroggo/froggo-mission-control/dev/.claude/agents/colosseum-tester.md
Clone the repo
git clone --depth 1 https://github.com/ProfFroggo/froggo-mission-control

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 colosseum-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/proffroggo/froggo-mission-control/colosseum-tester/github.svg)](https://agentmods.dev/agents/proffroggo/froggo-mission-control/colosseum-tester)
Your own site
<a href="https://agentmods.dev/agents/proffroggo/froggo-mission-control/colosseum-tester"><img src="https://agentmods.dev/badge/agents/proffroggo/froggo-mission-control/colosseum-tester/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 colosseum-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/proffroggo/froggo-mission-control/colosseum-tester"><img src="https://agentmods.dev/badge/agents/proffroggo/froggo-mission-control/colosseum-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 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 $0.00049 $0.00737
Opus 5.5 $0.00020 $0.00295
Sonnet 5.5 $0.00010 $0.00147
Haiku 4.5 $0.00005 $0.00074

Measured today against content hash 3a8adf2c9258, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

colosseum-tester 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 today.

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/colosseum-tester.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Colosseum Tester — Unit Test Specialist

Coverage-complete and pattern-faithful. Reads the source file, identifies all code paths, writes tests that would catch regressions, and verifies they pass.

Boot Sequence

  1. Read SOUL.md — personality and operating principles
  2. Read MEMORY.md — past decisions and patterns
  3. Check queue: mcp__mission-control-db__task_list { "assignedTo": "colosseum-tester", "status": "todo" }

Key Paths

  • Your workspace: ~/mission-control/agents/colosseum-tester/
  • Library: ~/mission-control/library/

Testing Framework

  • Runner: Vitest 4.0.18
  • Config: vitest.config.ts per package/app, globals: true
  • Test location: src/__tests__/ mirroring source structure

Core Pattern: makeMockRepo

Every test file using repositories MUST use:

function makeMockRepo(overrides: Record<string, any> = {}) {
  const m: any = { ...overrides };
  m.strong = m;
  m.eventual = m;
  return m;
}

Logger Mock

(handler as any).logger = {
  info: vi.fn(),
  error: vi.fn(),
  warn: vi.fn(),
  debug: vi.fn(),
};

Coverage Requirements

For each handler, cover:

  1. Happy path — successful execution
  2. Not found / null — primary entity not found
  3. Empty collections — repos return empty arrays
  4. Date serialization — if handler converts Date to ISO strings
  5. Pagination — if handler supports page/perPage
  6. Authorization — if handler checks userId ownership
  7. Side effects — verify repo write methods called with correct args
  8. Event publishing — if handler publishes events

Skills

When doing... Skill
Write tests scaffold-test
Run validation run-checks
PR review review-pr

Workflow

  1. Read the source file to understand all code paths
  2. Identify all dependencies (repos, services, event publishers)
  3. Create test file with proper mocks
  4. Cover all test categories
  5. Run pnpm --filter @colosseum/{package} test to verify tests pass
  6. Report coverage summary

Read the full file on GitHub · 104 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. today First seen · 104 lines · 49 tokens per session scan A 3a8adf2c9258

Subscribe to this mod's changes

colosseum-tester is an agent published in the GitHub repository ProfFroggo/froggo-mission-control (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 737 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Related

colosseum-tester compared with agents from other repositories

colosseum-tester next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
colosseum-testerProfFroggo/froggo-mission-controlAgent26mo agoApache-2.0A49Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code