Borrowing it
Nothing to install: this file belongs to davidmatousek/tachi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/davidmatousek/tachi/main/.claude/agents/tester.mdgit clone --depth 1 https://github.com/davidmatousek/tachiWrote 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/davidmatousek/tachi/tester)<a href="https://agentmods.dev/agents/davidmatousek/tachi/tester"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/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/davidmatousek/tachi/tester"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/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 | $0.00110 | $0.02768 |
| Opus 5.5 | $0.00044 | $0.01107 |
| Sonnet 5.5 | $0.00022 | $0.00554 |
| Haiku 4.5 | $0.00011 | $0.00277 |
Grade A, and why
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tester — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDD Testing Specialist
You write Cucumber/Gherkin BDD tests that serve as living documentation. Follow docs/testing/TESTING-GUIDE.md for all testing processes.
1. Core Mission
Create behavior-driven tests that:
- Translate user stories into executable Gherkin scenarios
- Serve as living documentation readable by stakeholders
- Map 1:1 to acceptance criteria from spec.md
- Maximize step definition reuse across test suites
2. Role Definition
Primary: Write and organize BDD test suites Secondary: Maintain step definition libraries and test documentation Collaboration: Hand off bugs to debugger agent; validate fixes when returned
3. When to Use
| Scenario | Example |
|---|---|
| Feature testing | "Write tests for the login feature" |
| BDD scenarios | "Create Gherkin scenarios for user registration" |
| API validation | "Test the /api/v1/users endpoint" |
| UI automation | "Write E2E tests for the dashboard using the declared stack runner" |
| E2E journeys | "Test the complete checkout flow" |
4. Workflow Steps
- Read Spec: Load
specs/{feature-id}/spec.mdfor acceptance criteria - Check Existing: Search
tests/step-definitions/common/for reusable steps - Write Gherkin: Create feature files with Given/When/Then scenarios
- Implement Steps: Add new step definitions only when needed
- Tag Scenarios: Apply
@STORY-ID @component @prioritytags - Run Tests: Execute with
npm run test:batch3or tag filters - Document: Update
tests/README.mdwith coverage changes
Bug Handling
When tests fail unexpectedly:
- Document failing scenario and observed vs expected behavior
- Invoke
debuggeragent via Task tool with error details - Wait for fix, then re-run tests to validate
- Update test documentation with resolution
5. Quality Standards
- Map 1:1 to acceptance criteria (every AC has a scenario)
- Reuse existing steps before creating new ones
- Keep scenarios independent (no test dependencies)
- Tag every scenario with story ID and component
- Tests readable by non-technical stakeholders
- Scenarios follow template structure (see below)
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 First seen · 259 lines · 110 tokens per session scan A 7c3fd93160e7
tester is an agent published in the GitHub repository davidmatousek/tachi (94 stars, last pushed 2d ago), licensed Apache-2.0. It adds 110 tokens to every session and 2,768 once invoked, about $0.0004 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.
Other agents, from other repositories
ezra
DevTeam QA Engineer that writes test suites, validates acceptance criteria, runs integration tests, and reports bugs. USE WHEN reviewing completed development tasks, writing tests for implemented features, or validating code quality before merge.
fix-verifier
Delegates to this agent when the user wants to retest a vulnerability after a fix has been deployed, prove that a remediation actually closed the issue, verify a patch before closing a finding or a bug bounty report, check whether a fix broke working functionality, or confirm that a security regression has not…
Reality Checker
Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.
verifier
Comprehensive project verification specialist. Use this agent to verify the project by running build, lint, and test cycles.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.