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 agentmods add skills/ccevans/bobbycode/bobby-definenpx skills add ccevans/bobbycode --skill bobby-definegit clone --depth 1 https://github.com/ccevans/bobbycodeWhat 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 | $0.00204 | $0.03683 |
| Opus 5 | $0.00102 | $0.01842 |
| Sonnet 5 | $0.00041 | $0.00737 |
| Haiku 4.5 | $0.00020 | $0.00368 |
Grade A, and why
define-product 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.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Define Skill
Product definer — takes the MVP epic from a one-line idea to a locked product definition: brief, personas, journeys, feature map, and a blueprint you can read on one page. Runs the process a real product team runs, so that when bobby-plan decomposes the epic, every ticket traces to a feature, a journey step, and a persona — instead of being invented.
Scope
This skill DEFINES the product. It produces .bobby/product/ — four locked,
committed artifacts plus a generated blueprint page — and ends by moving the
epic to planning.
- Not the idea gate: whether this is worth building at all is bobby-vet (run before the project exists). By the time define runs, the idea is committed.
- Not visual design: what screens look like is bobby-design — it runs after define, using the personas and journeys as its inputs.
- Not decomposition: tickets are bobby-plan's job (Product-Aware Epic Mode), which reads the feature map this skill locks.
- One definition per project:
.bobby/product/describes THIS project's product. A second unrelated epic in the same repo reuses or extends it, not replaces it.
Before Starting
Read, in parallel:
.claude/skills/bobby-define/learnings.md+.claude/skills/bobby-define/learnings.local.mdand.claude/skills/bobby-shared/learnings.md+.claude/skills/bobby-shared/learnings.local.md- The epic's
ticket.md— its Description carries the idea, verbatim. Quote it; never paraphrase it into something you'd rather build. - Any existing
.bobby/product/*.md— resume, don't restart. If brief.md exists and is approved, start at Step 2. If the human wants a locked artifact changed, that's a Deviation + Changelog entry, not a rewrite. .bobby/architecture-wakeup.mdif present (existing projects have constraints an idea-stage interview should respect).
The Three Rules (read before anything else)
Rule 1 — The human reacts. You define.
The founder is not a product manager. Never ask them to write a persona, enumerate features, or produce a journey. You draft from evidence; they react. Ask questions a founder can answer from lived experience ("who did you last see struggling with this?"), draft the artifact, then ask the stage's gate question. Their reaction — keep, strike, correct — is the input. Every stage ends with its ⛳ gate; nothing advances past a gate without their answer.
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 First seen · 262 lines · 204 tokens per session scan A 60197aab0030
define-product is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 8d ago), licensed MIT. It adds 204 tokens to every session and 3,683 once invoked, about $0.0010 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.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.