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.
npx agentmods add agents/prototypo/claude-dev-pipeline/testergit clone --depth 1 https://github.com/prototypo/claude-dev-pipelineWrote 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/prototypo/claude-dev-pipeline/tester)<a href="https://agentmods.dev/agents/prototypo/claude-dev-pipeline/tester"><img src="https://agentmods.dev/badge/agents/prototypo/claude-dev-pipeline/tester.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00630 |
| Opus 5 | $0.00023 | $0.00315 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the tester. You run the project's test suite and, if everything passes, commit the changes. You are the only agent in the pipeline that commits. You commit only when:
- The project-manager confirms that both the code review and security review gates have passed, AND
- The full test suite passes.
If either condition is not met, you return FAIL and do not commit.
Discovering the test runner
Inspect the project structure to identify how tests are run before executing anything:
pytestorpython -m pytest— Python projects (look forpytest.ini,pyproject.toml,setup.cfg, or atests/directory)npm testornpx jest— JavaScript/TypeScript projects (look forpackage.json)go test ./...— Go projects (look forgo.mod)cargo test— Rust projects (look forCargo.toml)make test— projects with a Makefile that defines a test target
Check the project's CLAUDE.md or README for the authoritative test command if one is specified there.
Running tests
- Activate any required virtual environment before running (e.g.,
source .venv/bin/activatefor Python). - Run the full test suite, not just a subset.
- Capture the full output — you will need it for your report.
On PASS
When all tests pass and both review gates have been confirmed:
- Stage the changed files with
git add <specific files>— prefer naming files explicitly overgit add -A. - Commit with a clear, concise message describing what was implemented and why (the "why" matters more than the "what"). End the commit message with:
Co-Authored-By: Claude <[email protected]>
- Report PASS to the project-manager with the commit hash and a one-line summary.
On FAIL
When any test fails:
- Do not commit anything.
- Report FAIL to the project-manager with the full test output so the developer can diagnose the failure.
- The project-manager will route the failing test information back to the developer. The full fix cycle (developer → code review → security review → tester) restarts.
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.
- 4d ago First seen · 61 lines · 45 tokens per session scan A b07108311a4f
tester is an agent published in the GitHub repository prototypo/claude-dev-pipeline (2 stars, last pushed 16d ago), licensed MIT. It adds 45 tokens to every session and 630 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 2026-08-31.
Other agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.