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-vetgit 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-vet)<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-vet"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-vet/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-vet"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-vet.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 | $0.00060 | $0.01769 |
| Opus 5.5 | $0.00024 | $0.00708 |
| Sonnet 5.5 | $0.00012 | $0.00354 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
vet-idea 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 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.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Vet Skill
Stress-tests ideas before they enter planning. Asks probing questions one at a time, challenges assumptions, explores alternatives, maps decision dependencies, and refines ticket descriptions.
Before Starting
- Check learnings — Read
.claude/skills/bobby-vet/learnings.md+.claude/skills/bobby-vet/learnings.local.md - Read the ticket (if one was provided) — title, description, acceptance criteria
- Read the parent epic (if
parentfield exists) — understand the broader feature context - Scan the backlog —
bobby ticket list backlogto check for related or duplicate tickets
Core Methodology: Sequential Interrogation
<interrogation_rules> These rules define bobby-vet's behavior. Follow them strictly:
-
ONE question at a time. Never ask multiple questions in a single message. Each message contains exactly one probing question, plus optionally a brief observation that motivated it.
-
Wait for the answer. Do not proceed to the next question until the user has responded.
-
Go deep before going wide. If an answer reveals an assumption or gap, follow that thread with 2-3 more questions before moving to a new topic.
-
No leading questions. Ask open questions that could go multiple ways: "What happens when..." not "Don't you think we should..."
-
Name what you're probing. Start each question with a bracketed label so the user can track the investigation: [Scope], [Users], [Edge Case], [Dependency], [Alternative], [Priority], [Risk], [Data Model], [Integration], [Migration]. </interrogation_rules>
Procedure
Phase 1: Understand (3-5 questions)
Goal: Fully understand the idea before challenging it.
Question categories:
- [Scope] What is the core problem this solves? Who asked for it and why?
- [Users] Who are the primary users? How do they solve this problem today?
- [Priority] Why now? What happens if we don't build this for 6 months?
- [Success] How will we know this worked? What metric moves?
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 · 176 lines · 60 tokens per session scan A 75908ae58048
vet-idea is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 1,769 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
wttr-weather
Weather via wttr.in GET (no key). Use for weather/forecast; prefer os.http.request.
engineering-principles
Practical engineering judgement: smallest change, subtract before adding, data structures before logic, idempotent operations, migrate callers then delete. Use when designing, building, or reviewing changes.
scheduling
Scheduling across time zones: confirm times in the attendee's own zone, use IANA zone names, mind DST edges, buffers and calendar etiquette. Use when booking meetings or calls with people in other zones.
agent-desktop
Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation. Apply when a task needs application launching, accessibility snapshots, stable element refs, window focusing, semantic clicks/typing, or visual confirmation outside the browser sandbox.
docs-page-style
House style and structure for uploads.sh documentation pages — the MDX subject pages under apps/web/src/content/docs/ (and the docs.astro hub) built on DocsLayout. Use this whenever you write, restructure, trim, or review a docs page: requests like "clean up the galleries docs", "this docs page has too much prose"…
contract
Reference convention for sub-agent I/O schemas. Loaded by orchestrator skills via /contract and into agents via the skills: field.