agentmods.dev

aidb: Skill for Claude Code

.claude/skills/testing-strategy/SKILL.md

testing-strategy is a skill for Claude Code from ai-debugger-inc/aidb. It costs 29 tokens per session (3,597 once invoked), scanned A, original, Apache-2.0.

A testing guide for AIDB, an AI debugging system. It prioritizes end-to-end tests, which check complete user workflows, before integration and unit tests, and defines how tests should be run.

In plain words
What is it for?
Use it to create or change AIDB tests, test debugging protocols and MCP tools, validate adapters, and run the relevant test suites through dev-cli.
Why use it?
It provides a consistent way to test the system and catch problems across its full stack. It also avoids unsupported test commands and helps diagnose failures in debugging tools and adapters.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ai-debugger-inc/aidb's own configuration. It tells Claude Code how to work on aidb 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 aidb configures →

not rated 21repo 5mo ago A scan 29 tokens original Apache-2.0
View source ↗ ai-debugger-inc/aidb ai-debugger.com
Reuse

Borrowing it

Nothing to install: this file belongs to ai-debugger-inc/aidb. 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/ai-debugger-inc/aidb/main/.claude/skills/testing-strategy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ai-debugger-inc/aidb

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 testing-strategy

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-debugger-inc/aidb/testing-strategy/github.svg)](https://agentmods.dev/skills/ai-debugger-inc/aidb/testing-strategy)
Your own site
<a href="https://agentmods.dev/skills/ai-debugger-inc/aidb/testing-strategy"><img src="https://agentmods.dev/badge/skills/ai-debugger-inc/aidb/testing-strategy/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 testing-strategy

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-debugger-inc/aidb/testing-strategy"><img src="https://agentmods.dev/badge/skills/ai-debugger-inc/aidb/testing-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,597 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 $0.00029 $0.03597
Opus 5.5 $0.00012 $0.01439
Sonnet 5.5 $0.00006 $0.00719
Haiku 4.5 $0.00003 $0.00360

Measured 2mo ago against content hash 3a44911c1654, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

testing-strategy 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 2mo 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/testing-strategy/SKILL.md · 465 lines

How it starts

The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIDB Testing Strategy

Priority: E2E → Integration → Unit (Highest ROI First)

CRITICAL: Test Execution Command

All tests MUST be run via ./dev-cli test run:

./dev-cli test run -s {suite} [-k 'pattern'] [-l {lang}]
  • Multiple -k and -l flags supported
  • NEVER use --local - suites know their natural execution environment; forcing local causes unexpected behavior
  • Direct pytest invocation is NOT supported

This skill guides you through creating and modifying tests for the AIDB project. The test infrastructure is complete - your job is to implement tests using proven patterns.

When implementing tests, you may also need:

  • adapter-development - Tests validate adapter behavior across languages
  • mcp-tools-development - MCP tools tested with DebugInterface abstraction
  • dap-protocol-guide - Tests exercise DAP protocol flows end-to-end
  • ci-cd-workflows - For testing CI/CD workflows themselves (not application code)

Core Philosophy

For complete test architecture, see test infrastructure in src/tests/.

1. E2E First, Unit Last

Why E2E First?

  • Validates real user workflows
  • Exercises the full stack (catches integration bugs early)
  • Most bugs discovered when testing actual components
  • Higher ROI than unit tests initially

Testing Priority:

  1. E2E Tests - Complete workflows, real programs, full integration
  2. Integration Tests - Component interactions, adapter lifecycle, state management
  3. Unit Tests - Edge cases, specific logic, error handling

2. Framework Tests: Keep It Simple

Goal: Verify we can launch and debug programs using various frameworks

Pattern:

  1. Connect to framework app (Django, Express, Spring Boot, etc.)
  2. Quick smoke test: set breakpoint → inspect → step
  3. That's it. Don't test framework internals.

Read the full file on GitHub · 465 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 465 lines · 29 tokens per session scan A 3a44911c1654

Subscribe to this mod's changes

testing-strategy is a skill published in the GitHub repository ai-debugger-inc/aidb (21 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,597 once invoked, about $0.0001 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 2026-08-30.

E2E testingLLMTestingaiai-agentsdeveloper-toolse2eframeworkintegrationllmsmcpunit
Related

testing-strategy compared with skills from other repositories

testing-strategy next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
testing-strategyai-debugger-inc/aidbSkill215mo agoApache-2.0A29Claude Code
aif-testainative-build/skillsSkill1015d agoMITA28Claude Code
hs-testUnibean9/harness-skillsSkill181mo agononeA84Claude Code, Codex
enterprise-integration-testingproffesor-for-testing/agentic-qeSkill525yesterdayMITA55Claude Code
scenario-testing2389-research/scenario-testingSkill35d agoMITA53Claude Code
integration-testingApexIQ/skillsmithSkill57mo agoMITA26Claude Code, Codex
nestjs-testingFilippoDeSilva/skillsSkill24mo agononeA43Claude Code, Codex