multi-agent-system-pattern: Skill for Cursor

.cursor/skills/tdd-agent-loops/SKILL.md

tdd-agent-loops is a skill for Cursor from vpeetla-ai/multi-agent-system-pattern. It costs 48 tokens per session (353 once invoked), scanned A, original, MIT.

A test-driven development workflow for AI agent systems, including agents made of connected steps and decision paths. TDD means writing a failing test, making it pass, then improving the code.

In plain words
What is it for?
Use it when adding agent nodes, fixing loops, or building agent patterns, with mocked model responses, asynchronous Python tests, routing checks, and integration tests.
Why use it?
It catches incorrect routing and agent-loop behavior without depending on live language-model responses, which can be inconsistent.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is vpeetla-ai/multi-agent-system-pattern's own configuration. It tells Cursor how to work on multi-agent-system-pattern 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 multi-agent-system-pattern configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vpeetla-ai/multi-agent-system-pattern. 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/vpeetla-ai/multi-agent-system-pattern/main/.cursor/skills/tdd-agent-loops/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vpeetla-ai/multi-agent-system-pattern

Made for: Cursor.

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 tdd-agent-loops

README.md
[![agentmods](https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/tdd-agent-loops.svg)](https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/tdd-agent-loops)
Your own site
<a href="https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/tdd-agent-loops"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/tdd-agent-loops.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 353 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 $0.00048 $0.00353
Opus 5 $0.00024 $0.00177
Sonnet 5 $0.00010 $0.00071
Haiku 4.5 $0.00005 $0.00035

Measured 7d ago against content hash 26c8e7ebe7c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tdd-agent-loops 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 7d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/skills/tdd-agent-loops/SKILL.md · 54 lines

What it actually says

TDD for Agent Loops

Inspired by mattpocock/skills tdd — adapted for LangGraph.

Red → Green → Refactor

  1. Red — Write failing test for routing or node output (mock LLM)
  2. Green — Minimal node/routing fix
  3. Refactor — Extract helpers only when second test needs it

What to test

Layer Test
Routing route_after_quality returns retry/pass/escalate
Nodes Given state in, partial state out (no real LLM)
Integration Full graph with FakeLLM fixture
Repo-fix Clone fixture repo, assert branch + patch count

Fixtures

@pytest.fixture
def fake_llm():
    return FakeLLM(responses=[{"content": "..."}])

Async

@pytest.mark.asyncio
async def test_graph_happy_path(tmp_path):
    ...

Avoid

  • Tests that only assert "graph compiles"
  • Snapshotting full LLM prose (flaky)
  • Hitting live Groq in CI

Reference

  • loop-engine-agent-platform/tests/test_repo_fix.py
  • *-agent-pattern/tests/ — minimal pattern coverage
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. 7d ago First seen · 54 lines · 48 tokens per session scan A 26c8e7ebe7c5

Subscribe to this mod's changes

tdd-agent-loops is a skill published in the GitHub repository vpeetla-ai/multi-agent-system-pattern (2 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 353 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

spec-code-review

Structured code review for bugs, regressions, tests, and standards. Report-only by default; apply fixes only when the current user or upstream caller explicitly requests review-and-fix. mode:agent is always report-only.

ronronner02/codepilot-agent · 48 tokens

spec-debug

Diagnosis loop for bugs and failing behavior. Use for errors, stack traces, regressions, failed tests, issue-tracker bugs, stuck investigations after failed fixes, or asks to debug/fix a bug.

ronronner02/codepilot-agent · 44 tokens

cuml-machine-learning

Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.

langchain-ai/deepagents · 43 tokens

python-testing

Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.

microsoft/agent-framework · 29 tokens

python-code-quality

Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.

microsoft/agent-framework · 40 tokens

notebooklm

Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…

teng-lin/notebooklm-py · 79 tokens