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-testgit 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-test)<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-test"><img src="https://agentmods.dev/badge/skills/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/skills/ccevans/bobbycode/bobby-test"><img src="https://agentmods.dev/badge/skills/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 | $0.00059 | $0.03889 |
| Opus 5.5 | $0.00024 | $0.01556 |
| Sonnet 5.5 | $0.00012 | $0.00778 |
| Haiku 4.5 | $0.00006 | $0.00389 |
Grade B, and why
test-ticket scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- `curl -X POST -H "Content-Type: application/json" -d '{...}'` for write operations Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl -s -o /dev/null -w "%{http_code}" <your dev server URL>` (app — configure `health_checks` in .bobbyrc.yml) How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Test Skill
Bug hunter, not spec runner. Finds bugs by exercising the running app — browser automation, API calls, direct runtime execution. NEVER runs the test suite (rspec/jest/npm test) — build and review already did that. Running specs here is a critical error.
Hard Rules
- NEVER run any spec/test runner — no
npm test,rspec,jest,pytest,dotnet test,go test, or any unit/integration test command. The build agent writes specs (TDD) and the review agent runs them independently. Running specs here is redundant and wastes the testing budget. - NEVER verify behavior by reading source code — you verify by observing the live app.
- If a test case cannot be verified through the live app, mark it BLOCKED — do not fall back to running specs as a substitute.
Before Starting
- Check learnings — Read
.claude/skills/bobby-test/learnings.md+.claude/skills/bobby-test/learnings.local.md - Read the ticket's
ticket.mdandtest-cases.md - Read
plan.mdto understand what was implemented
Health Check
Verify the dev environment is running before testing:
curl -s -o /dev/null -w "%{http_code}" <your dev server URL>(app — configurehealth_checksin .bobbyrc.yml)
Required Services
The web server is not enough. Read plan.md to identify ALL services the feature depends on — background workers (Sidekiq, Celery, Bull), message queues, caches, etc. Verify each one is running:
- Web server — health check above
- Background workers — check if the worker process is running (e.g.,
docker compose ps,ps aux | grep sidekiq). If not running, start it:docker compose up -d sidekiqor the equivalent. - Databases / caches — verify connectivity if the feature depends on Redis, Elasticsearch, etc.
Service Recovery
If a service isn't running or a health check fails, attempt one restart per service:
-
Web: Run
npm run devin the background -
Workers:
docker compose up -d sidekiqor the project's equivalent -
Wait up to 15 seconds, then re-check
-
If it doesn't come back after one attempt, mark affected tests as BLOCKED
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.
- yesterday Changed · +4 lines 14bf98dcbd19
- 1mo ago First seen · 308 lines · 59 tokens per session scan B 1574aca16b78
test-ticket is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 3,889 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, 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.