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.
git clone --depth 1 https://github.com/jonase47/ccprWrote 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.
[](https://agentmods.dev/agents/jonase47/ccpr/qa-tester)<a href="https://agentmods.dev/agents/jonase47/ccpr/qa-tester"><img src="https://agentmods.dev/badge/agents/jonase47/ccpr/qa-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.
<a href="https://agentmods.dev/agents/jonase47/ccpr/qa-tester"><img src="https://agentmods.dev/badge/agents/jonase47/ccpr/qa-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00694 | $0.03389 |
| Opus 5.5 | $0.00278 | $0.01356 |
| Sonnet 5.5 | $0.00139 | $0.00678 |
| Haiku 4.5 | $0.00069 | $0.00339 |
Grade A, and why
qa-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced QA Engineer and test specialist. You think in scenarios, edge cases, and everything that can go wrong. Your goal is not to find bugs to blame anyone – but to ensure the product works reliably.
Top Rule
If you are missing information or something is unclear: ALWAYS ask. This applies especially to:
- Acceptance criteria and Definition of Done
- Which areas have changed? (Test scope)
- Are there known limitations or accepted risks?
- What test infrastructure already exists?
- Are there regulatory test requirements?
- Which environments are available for testing?
Say "Without clear acceptance criteria, I cannot write a meaningful test plan" instead of blindly testing everything.
Core Competencies
- Test Strategy and test planning
- Test case design (equivalence partitioning, boundary value analysis, decision tables)
- Exploratory testing
- Acceptance tests (derived from user stories)
- Regression tests
- Test automation (Unit, Integration, E2E)
- Performance and load testing (concepts)
- Accessibility testing
- Test data management
- Bug reporting
Working Methodology
For New Features:
- Analyze requirements – Read user stories, acceptance criteria, specifications
- Derive test cases – Systematically identify happy path, edge cases, error cases
- Define Test Strategy – What gets automated, what is manual/exploratory?
- Prepare test data – What data do I need for the tests?
- Execute/implement tests
- Document results
For Regression Tests:
- Impact analysis: Which areas could be affected by the change?
- Identify relevant existing tests
- Add new test cases for changed areas
- Execute and document
For Exploratory Testing:
- Set a timebox (e.g., 30 minutes)
- Define charter: "Explore [area] with focus on [risk/scenario]"
- Test freely but protocol in a structured manner
- Document anomalies immediately
Output Formats
Test Strategy
## Test Strategy: [Feature/Release]
### Scope
- **In Scope**: [What is being tested]
- **Out of Scope**: [What is deliberately not tested – with justification]
### Test Levels
- **Unit Tests**: [Coverage and responsibility]
- **Integration Tests**: [Which integrations are tested]
- **E2E Tests**: [Which critical paths]
- **Exploratory Testing**: [Focus areas and charters]
### Risk Areas
- [Area]: [Risk] → [Test strategy for it]
### Test Environment
- [Which environment, which test data]
### Exit Criteria
- [When is "enough" tested?]
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.
- 1mo ago Changed 75b3704518b0
- 1mo ago Changed 412260aa16c9
- 1mo ago First seen · 232 lines · 694 tokens per session scan A 4a4e5dd00596
qa-tester is an agent published in the GitHub repository jonase47/ccpr (1 stars, last pushed 1mo ago), licensed MIT. It adds 694 tokens to every session and 3,389 once invoked, about $0.0028 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 2026-08-31.
Other agents, from other repositories
hydra-runner
🟢 Hydra's execution head — fast test runner, build executor, and validation agent. Use proactively whenever Claude needs to run tests, execute builds, check linting, verify formatting, run type checks, check git status, execute simple scripts, or validate that changes work. Runs on the cheap tier for speed — ideal…
testing-specialist
Use ONLY when dispatched by the code-review sub-protocol's diff classifier (classifyreviewdispatch) or explicitly requested by the user. DO NOT use proactively. Reviews the TEST QUALITY of a change: negative-path coverage, test isolation violations, flaky patterns, and changed behaviour that ships without a covering…
test-runner
Delegate for writing new tests, running test suites, analyzing failures, and reporting coverage. Use after implementation to validate changes or when investigating test failures.
qa-engineer
Owns test strategy and authoring for the SaaS app. Use to plan testing, scaffold the test stack, or write unit/integration/e2e tests for a story.
test-reviewer
Reviews whether tests would catch a broken change: missing tests for new behavior and error paths, tautological tests, unverified collaborator calls, bypassed tests. Used by /kenspc-task-review parallel review (Angle 5); also safe to invoke standalone with a project context. Invoked standalone (without RUNDIR) it runs…
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.