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-plangit 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-plan)<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-plan"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-plan/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-plan"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-plan.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 | $0.00052 | $0.04015 |
| Opus 5.5 | $0.00021 | $0.01606 |
| Sonnet 5.5 | $0.00010 | $0.00803 |
| Haiku 4.5 | $0.00005 | $0.00402 |
Grade A, and why
plan-ticket 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Plan Skill
This skill handles planning — both epic breakdown and ticket refinement.
Before Starting
- Check learnings — Read
.claude/skills/bobby-plan/learnings.md+.claude/skills/bobby-plan/learnings.local.md - Read the ticket — Understand what's being asked
Investigation First
<investigation_rules> Before creating any plan:
- Read the ticket's title, description, and acceptance criteria fully
- If the ticket has a
parentfield, read the parent epic's ticket.md and plan.md - If the ticket has a
featurefield, read.bobby/product/feature-map.md(that row and the journey step(s) it serves) and.bobby/product/personas.md— the AC must satisfy the journey step, and test-cases.md should exercise it as the persona - Read any existing
feature-plan.mdto understand cross-cutting decisions already made - If you are unsure about the scope of an AC, improve the AC text rather than guessing
- Explore the codebase to understand existing patterns before proposing new ones
- Large file discipline: For files over 500 lines (CSS, large components, mockups), do NOT read the entire file. Instead, grep for the relevant section name or keyword to find the line range, then read only that range. Record useful line ranges in the plan's
## Files to modifysection so downstream agents (build, review) can do targeted reads too. </investigation_rules>
Mode Detection
- If the ticket has
type: epicAND.bobby/product/feature-map.mdexists → Product-Aware Epic Mode (decompose against the locked definition) - If the ticket has
type: epic→ Epic Mode (break down into child tickets) - If the ticket is in
planningstage AND has aparentfield (belongs to an epic) → Feature-Aware Refine Mode (plan with sibling context) - If the ticket is in
planningstage with noparent→ Refine Mode (create plan + test cases)
Product-Aware Epic Mode
The epic went through the define pipeline: .bobby/product/ holds a locked
brief, personas, journeys, and feature map. Scope was decided at the human
gates — you do not re-decide WHAT to build. Approach scoring still applies to
HOW.
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 · 381 lines · 52 tokens per session scan A 4973171a6918
plan-ticket is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 4,015 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
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
aiox-pm
Activate Morgan (pm) for Product Manager. Use for PRD creation (greenfield and brownfield), epic creation and management, product strategy and vision, feature prioritization (MoSCoW, RICE), roadmap planning, business case development, go...
aiox-po
Activate Pax (po) for Product Owner. Use for backlog management, story refinement, acceptance criteria, sprint planning, and prioritization decisions.
aiox-squad-creator
Activate Craft (squad-creator) for Squad Creator. Use to create, validate, publish and manage squads.
full-sdc
EXECUTE lean Full Story Development Cycle for one story: plan via CLI, run validate → develop → review (QG loop) → close with Sequence Lock, durable progress under .aiox/sdc/. Use when: full-sdc, full cycle, SDC, run story end-to-end.
wave-execute
EXECUTE a lean wave — plan story DAG + file-ownership batches via CLI, dispatch full-sdc per story, fan-in check, hand off merge to @devops. Use when: wave-execute, run wave, epic wave, parallel stories SDC.