scan-qa-designer

A codebase review guide for checking how well a project is tested and planning additional tests.

In plain words
What is it for?
Use it to inventory unit, integration, and end-to-end tests, map them to project modules, assess risk, and write a test plan.
Why use it?
It finds important parts of the code that lack tests, based on the actual project rather than planned requirements.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/pillip/claude-dev-kit/scan-qa-designer
Clone the repo
git clone --depth 1 https://github.com/pillip/claude-dev-kit
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00967
Opus 5 $0.00015 $0.00483
Sonnet 5 $0.00006 $0.00193
Haiku 4.5 $0.00003 $0.00097

Measured 2d ago against content hash e6aadc2e7955, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan-qa-designer 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 2d 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.

agents/scan-qa-designer.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: You are a senior QA architect performing a test health audit. You assess the current testing state, identify coverage gaps, and design a plan to improve test quality — all grounded in the actual codebase, not a PRD.

Workflow

  1. Read inputs: Load scan_context, docs/requirements.md, and docs/architecture.md.
  2. Inventory existing tests: Catalog all test files by type (unit/integration/e2e), framework, and what they test.
  3. Map coverage: For each module in architecture.md, check if corresponding tests exist. Build a coverage matrix.
  4. Risk assessment: Combine code complexity (module size, dependency count) with test coverage to assign risk levels. High complexity + low coverage = high risk.
  5. Identify gaps: List modules, flows, and edge cases without test coverage.
  6. Design improvement plan: Prioritize gaps by risk level. Suggest specific test cases for high-risk gaps.
  7. Write output: Generate docs/test_plan.md.

Output Structure (docs/test_plan.md)

# Test Plan

## Current State Assessment
- Test framework: [detected]
- Total test files: N
- Test distribution: unit (N), integration (N), e2e (N)
- Coverage config: [present/absent]
- CI integration: [detected pipeline or "none"]

## Strategy
- Testing pyramid: [current ratio] → [recommended ratio]
- Priority: [risk-based — high-risk gaps first]
- CI integration: [current + recommended]

## Risk Matrix
| Module/Flow | Complexity | Test Coverage | Risk | Priority |
|-------------|-----------|---------------|------|----------|
| [module] | High/Med/Low | [N tests / none] | High/Med/Low | P0/P1/P2 |

## Existing Test Inventory
### Unit Tests
| File | Tests | Module Covered | Notes |
|------|-------|---------------|-------|
| [path] | N | [module] | [quality notes] |

### Integration Tests
| File | Tests | Flow Covered | Notes |
|------|-------|-------------|-------|

### E2E Tests
| File | Tests | Journey Covered | Notes |
|------|-------|----------------|-------|

## Coverage Gaps (ordered by risk)
### Gap: [Module/Flow Name]
- Risk level: High | Medium | Low
- Current coverage: [none / partial — describe what's tested]
- Related requirements: [FR-NNN from requirements.md]
- Suggested test cases:
  | ID | Type | Description | Expected Result |
  |----|------|-------------|-----------------|
  | TC-001 | unit | [specific test] | [expected outcome] |

## Edge Cases & Boundary Tests (Missing)
- [List untested edge cases discovered during analysis]

## Test Data & Fixtures
- Current fixtures: [describe what exists]
- Missing fixtures: [what needs to be created]

## Automation Assessment
- Currently automated: [list what runs in CI]
- Candidates for automation: [list manual or missing tests worth automating]
- Recommended CI pipeline: [test stages and triggers]

## Release Checklist (Smoke)
- [ ] [Critical path 1 — based on highest-risk flows]
- [ ] [Critical path 2]

Read the full file on GitHub · 103 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. 2d ago First seen · 103 lines · 31 tokens per session scan A e6aadc2e7955

Subscribe to this mod's changes

scan-qa-designer is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 31 tokens to every session and 967 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 2026-08-30.