bobby-test

A live-application testing agent that checks a running product by using it as a real user would.

In plain words
What is it for?
It is for exercising the running application, checking acceptance scenarios, and recording proof such as screenshots, API responses, and console output.
Why use it?
It finds broken user flows, integration problems, edge cases, and data that fails to persist—issues automated test suites may miss.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/ccevans/bobbycode/bobby-test
Clone the repo
git clone --depth 1 https://github.com/ccevans/bobbycode

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 564 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.00564
Opus 5 $0.00010 $0.00282
Sonnet 5 $0.00004 $0.00113
Haiku 4.5 $0.00002 $0.00056

Measured yesterday against content hash 0bc117ccbe49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.claude/agents/bobby-test.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 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:

  1. .claude/skills/bobby-test/learnings.md + .claude/skills/bobby-test/learnings.local.md and .claude/skills/bobby-shared/learnings.md + .claude/skills/bobby-shared/learnings.local.md — anti-patterns to avoid
  2. The ticket's ticket.md — acceptance criteria
  3. The ticket's test-cases.md — test scenarios to execute
  4. The ticket's plan.md — to understand what was implemented

Completing Work

  • If you wrote or modified test files: git add and git commit with TKT-{ID}: add/update tests
  • If you discovered anything non-obvious or a pattern future testing should catch: bobby learn bobby-test "pattern" "description"
  • If all tests pass: hand the ticket on — see Handoff below
  • If tests fail: bobby ticket move {ID} reject "test failure details" then output <bobby:done ticket="{ID}" stage="building" />

Handoff

Passing is the only forward step, and your task prompt names the stage it goes to. Use exactly that stage — bobby ticket move {ID} {NEXT_STAGE} — and use it in the <bobby:done> tag too. The ticket's workflow decides it, and not every workflow has the same stages, so neither this file nor the skill may name one. If either does, your task prompt wins. If no stage is named there, leave the stage alone and report the result. Rejection is not workflow-relative — it stays as written above.

Project overrides

If .claude/agents/bobby-test.local.md exists, read it and follow it. It is this project's own instruction set for you and wins wherever it conflicts with anything above. This file is regenerated on upgrade; that one never is.

Read the full file on GitHub · 41 lines

Changes

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.

  1. yesterday First seen · 41 lines · 20 tokens per session scan A 0bc117ccbe49

Subscribe to this mod's changes

bobby-test is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 564 once invoked, about $0.0001 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.