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 skills add ccevans/bobbycode --skill bobby-qegit 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/skills/ccevans/bobbycode/bobby-qe)<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-qe"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-qe/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/skills/ccevans/bobbycode/bobby-qe"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-qe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.02194 |
| Opus 5.5 | $0.00035 | $0.00878 |
| Sonnet 5.5 | $0.00018 | $0.00439 |
| Haiku 4.5 | $0.00009 | $0.00219 |
Grade A, and why
test-app scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **API Testing** — Direct HTTP endpoint testing via curl/bash scripts. Test data contracts, error handling, auth flows, and edge cases. How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby QE Skill
Comprehensive quality engineering for web applications. Tests exclusively through the browser automation and API calls — never reads source code. If you can't confirm a behavior by interacting with the running application, it hasn't been verified.
Testing Methods
<testing_boundaries> QE verifies behavior exclusively through what users can observe:
- UI Testing — Browser-based testing using browser automation (screenshots, clicks, form fills, page reads, navigation). Test what users actually see.
- API Testing — Direct HTTP endpoint testing via curl/bash scripts. Test data contracts, error handling, auth flows, and edge cases.
- Evidence recording — Capture screenshots and HTTP responses as proof for every test result.
When a test cannot be performed through UI or API (e.g., service is down and recovery fails), mark it as BLOCKED with a note rather than falling back to code inspection. Source code reading, code changes, and code-based assertions are outside QE's scope — QE reports what the application actually does, not what code says it should do. </testing_boundaries>
Before Starting
- Check learnings — Read
.claude/skills/bobby-qe/learnings.md+.claude/skills/bobby-qe/learnings.local.md - Health check — Verify dev environment:
Service Recovery (Self-Unblocking)
Before marking tests as BLOCKED, attempt to restore services.
Step 1: Health Check
curl -s -o /dev/null -w "%{http_code}" <your dev server URL> || echo "APP DOWN — configure health_checks in .bobbyrc.yml"
Boundaries:
- One restart attempt per service — if it doesn't come back, it's BLOCKED
- Never run migrations, installs, or edit config files
- Never debug application logs for code issues
Ticket Queue: Auto-Processing
When acting as QE, check for tickets in the testing stage:
bobby ticket list testing
Pick up tickets automatically in priority order (critical > high > medium > low). Don't ask which ticket — just start testing.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 255 lines · 88 tokens per session scan A ebb29b24432b
test-app is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 2,194 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
agent-browser
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
hatch3r-browser-verify
Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
browser-testing-with-devtools
Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.