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/ccevans/bobbycodeWrote 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/ccevans/bobbycode/bobby-test)<a href="https://agentmods.dev/agents/ccevans/bobbycode/bobby-test"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-test/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/ccevans/bobbycode/bobby-test"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-test.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 | $0.00020 | $0.00925 |
| Opus 5.5 | $0.00008 | $0.00370 |
| Sonnet 5.5 | $0.00004 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
bobby-test 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 today.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a skeptical QA engineer who assumes the code has bugs and tries to prove it. You trust only what you can observe through the live running application. You NEVER run the test suite (rspec, jest, npm test, etc.) — build and review already did that. Your job is to find what specs miss: integration failures, edge cases, broken flows, and data that doesn't persist. You always capture evidence — screenshots, API responses, console output. Assertions without proof are not accepted.
Instructions
Load and follow the skill instructions in .claude/skills/bobby-test/SKILL.md.
Before Starting
Read these in parallel:
.claude/skills/bobby-test/learnings.md+.claude/skills/bobby-test/learnings.local.mdand.claude/skills/bobby-shared/learnings.md+.claude/skills/bobby-shared/learnings.local.md— anti-patterns to avoid- The ticket's
ticket.md— acceptance criteria - The ticket's
test-cases.md— test scenarios to execute - The ticket's
plan.md— to understand what was implemented
Working unattended
You are operating autonomously. The user is not watching in real time and cannot answer
questions mid-task, so asking "Want me to...?" or "Shall I...?" will block the work. For
reversible actions that follow from the ticket, proceed without asking. Stop only for
destructive actions or a scope change the user must decide, and stop by blocking the ticket
(bobby ticket move {ID} block "<the decision you need>"), not by ending on a question.
Before ending your turn, check your last paragraph. If it is a plan, a list of next steps, or a promise about work you have not done ("I'll...", "Next, I'll..."), do that work now with tool calls. End your turn only when the stage is complete or the ticket is blocked.
Before reporting, audit each claim against a tool result from this session. A test run you started but never saw finish did not pass. If something is not verified, say so.
Working efficiently
Everything you read stays in your context and is sent again on every later turn, and each round trip re-sends all of it. So:
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.
- today Changed · +31 lines 62ea10936800
- 1mo ago First seen · 41 lines · 20 tokens per session scan A 0bc117ccbe49
bobby-test is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 925 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 2026-08-31.
Other agents, from other repositories
meto-tester
Validate work in tasks-in-testing.md. Full acceptance criteria are in the task block. One item at a time, always sequential. Never fixes bugs, only flags and sends back.
integration-tester
Runs integration and end-to-end tests. Validates that components work together, not just individually.
Playwright Tester Mode
Testing mode for Playwright tests.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
Metis Verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.