- Home
- Skills
- Testing & Debugging
- Test Strategy Planner — Test What Matters Most
Works with the AI Agents you already use
Test Strategy Planner — Test What Matters Most
Prioritize testing effort by mapping module blast radius against the existing safety net.
$12
Test Strategy Planner — Test What Matters Most
Example session with this skill installed
Which modules in the src/auth directory are the riskiest to refactor right now, and what tests are missing?
- Read your context and instructions
- Compiled the test strategy planner
I have analyzed the src/auth directory. The analysis identified 3 modules, their transitive blast radius, and the current gaps in the safety net.
Test Strategy Plan: src/auth
1. The Inventory
The tool detected 4 test files attributed to the auth directory. A manual git ls-files check confirmed 5 files matching *.test.ts, indicating one integration test is currently not attributed to a specific module.
2. The Containment Map
| Module | Blast Radius | Safety Net | Gap |
|---|---|---|---|
src/auth/session | 8 modules, 42 files | 1 test file | Critical |
src/auth/crypto | 2 modules, 5 files | 3 test files | Low |
src/auth/providers | 1 module, 2 files | None | Medium |
3. Ordered Test Plan
Priority 1: src/auth/session
- The Stakes: High. This module is used by the entire routing and billing layer.
The Gap: Only one test file exists, and git grep shows the validateSession export is never mentioned in *.test.ts.
- Failure Caught: A regression here would allow unauthorized access to the billing dashboard.
- Test Location:
src/auth/session.test.ts - Verification: Assert that an expired token correctly triggers a 401 response in the router middleware.
Priority 2: src/auth/providers
- The Stakes: Low direct impact, but contains zero tests.
- The Gap: No attributed test files.
- Failure Caught: Failure to map OAuth profiles correctly during login.
- Test Location:
src/auth/providers.test.ts
4. Symbol-level Gaps
The following public exports have no mentions in any test files:
validateSession(src/auth/session)refreshMetadata(src/auth/providers)
Next steps
- Initialize
src/auth/session.test.tsto cover thevalidateSessioncontract. - Investigate the unattributed integration test found in the inventory phase.
- Add a basic provider mapping test to close the visibility gap in
src/auth/providers.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop guessing which files to test based on line coverage percentages that don't reflect risk. This skill identifies the gap between a module's blast radius and its existing safety net, helping you prioritize tests that prevent systemic failures.
What it does
- Blast radius mapping calculates exactly which modules and files break if a specific module fails.
- Safety net inventory audits existing test files and identifies which modules are currently unprotected.
- Contract gap analysis performs symbol-level checks to find public exports that no test mentions.
- Risk ranking prioritizes testing effort by joining transitive impact data with current test coverage.
- Read-only planning generates a structured test strategy without modifying your source code or test suites.
How it works
- Frame the question to define the specific risk profile, such as a pending release or a new team takeover.
- Inventory the safety net using the
agent-contextCLI orgitfallbacks to count attributed test files. - Measure exposure to determine the transitive impact of a module failure across the entire repository.
- Generate the containment map to visualize high-impact modules that lack sufficient protection.
- Produce the plan following a structured template that lists the failure each new test would catch.
Frameworks & tools
The skill is optimized for repositories using git and can utilize the optional ai-agent-context CLI for deep transitive analysis. It works with any testing framework that follows standard naming conventions (e.g., jest, vitest, mocha).
Why this beats prompting it yourself
Generic prompts often confuse file proximity with actual test coverage or fail to trace transitive dependencies. This skill uses a rigorous containment-map methodology to ensure you aren't just adding lines, but actually reducing the risk of a cascading failure.
Use cases
- Determine which modules are the riskiest to change before a major release.
- Identify public API exports that are completely missing from the test suite.
- Create a prioritized testing roadmap for a legacy codebase with low coverage.
- Validate that high-impact utility modules have a sufficient safety net.
Known limitations
Does not run tests or measure actual line coverage execution. Heuristic detection may miss test files that do not follow standard naming or call patterns. Analysis is read-only.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.
Read-only analysis only. Heuristic test detection may miss files not using standard naming or it/test calls. Does not measure runtime coverage.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 28 days ago
- Software
- ai-agent-context
Node.jsagent-context
Git