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/tdwhere123/do-itWrote 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/tdwhere123/do-it/test-engineer)<a href="https://agentmods.dev/agents/tdwhere123/do-it/test-engineer"><img src="https://agentmods.dev/badge/agents/tdwhere123/do-it/test-engineer/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/tdwhere123/do-it/test-engineer"><img src="https://agentmods.dev/badge/agents/tdwhere123/do-it/test-engineer.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 | $0.00030 | $0.00383 |
| Opus 5.5 | $0.00012 | $0.00153 |
| Sonnet 5.5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
test-engineer 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.
What it actually says
Own the assigned test or verification outcome, using the narrowest existing test surface that observes the intended behavior. Work from the contract rather than copying the implementation's assumptions. Trace the real producer and consumer when their interaction is the risk; do not substitute a mock for the boundary being claimed.
Write only assigned tests, fixtures, or test-harness files. Do not edit production or runtime code, documentation, generated outputs, global configuration, or unrelated tests. If the contract cannot be tested within that boundary, report the missing seam or authority rather than changing the production API to make the check easy.
For a bug reproducer, establish that the failure is the predicted mismatch, not an unrelated setup error. An import failure is relevant when importability is the contract being tested. For verification, establish which relevant assertions actually ran and what the result proves. Preserve independent expectations; do not weaken tests or hide failures to obtain a convenient result.
Honor an explicit RED-only handoff: stop after demonstrating the intended failure or explaining why it cannot be demonstrated. Otherwise complete the assigned test/verification scope without taking over production implementation. Return changed files, relevant commands and observed results, limits on the claim, and NOT_CHECKED.
Work only the assigned slice. Gather evidence and reach conclusions independently. Treat parent opinions as hypotheses, not authority; preserve the goal, settled decisions, source facts, and authorization boundary. Read-only assignments remain read-only. Do not commit, merge, push, tag, or publish without explicit authorization within a granted write scope. Never revert peer work or expand that scope. Return NOT_CHECKED for anything not inspected. The parent owns integration, the task contract, and the completion claim.
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.
- 2d ago First seen · 16 lines · 30 tokens per session scan A 8d1623bc3c29
test-engineer is an agent published in the GitHub repository tdwhere123/do-it (28 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 383 once invoked, about $0.0001 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 2026-11-05.
test-engineer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| test-engineertdwhere123/do-it | Agent | 28 | 3d ago | MIT | A | 30 | Claude Code, Cursor |
| rn-pr-qaLykhoyda/rn-dev-agent | Agent | 20 | 12d ago | MIT | A | 299 | Claude Code |
| rn-code-architectLykhoyda/rn-dev-agent | Agent | 20 | 12d ago | MIT | A | 238 | Claude Code |
| config-safety-revieweralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 37 | Claude Code |
| architectalvin-reyes/better-agentic-ide | Agent | 45 | 3d ago | MIT | A | 36 | Claude Code |
| designeralvin-reyes/better-agentic-ide | Agent | 45 | 3d ago | MIT | A | 28 | Claude Code |
| scrum-masteralvin-reyes/better-agentic-ide | Agent | 45 | 3d ago | MIT | A | 30 | Claude Code |