A workflow guide for delivering a whole feature, or epic, across its related tickets. It plans the tickets together, then takes each through building, review, and testing on one feature branch.

Use it when an epic has several child tickets that need coordinated implementation and verification.

It helps expose integration problems between tickets and checks that the complete feature works as a group.

run-feature — Skill for Claude Code by ccevans/bobbycode

Install

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.

Any agent

npx skills add ccevans/bobbycode --skill bobby-feature

Clone the repo

git clone --depth 1 https://github.com/ccevans/bobbycode

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-feature/github.svg)](https://agentmods.dev/skills/ccevans/bobbycode/bobby-feature)

Your own site

<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-feature"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-feature/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-feature"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,807 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00077	$0.02807
Opus 5.5	$0.00031	$0.01123
Sonnet 5.5	$0.00015	$0.00561
Haiku 4.5	$0.00008	$0.00281

Measured 1mo ago against content hash 44d0aa811809, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

run-feature 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.

.claude/skills/bobby-feature/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bobby Feature Skill

Orchestrates a full feature (epic) across all its child tickets on a single branch. First plans ALL tickets holistically so each plan benefits from knowing its siblings, then builds/reviews/tests each sequentially. Catches integration issues between tickets and verifies the whole feature works before shipping.

Before Starting

Epic selection — If an epic ID was provided as an argument, use it. Otherwise, discover and present epics: a) Run bobby ticket list and identify tickets with type: epic b) For each epic, count children and summarize their stages c) Present the results:

Available Epics:

Epic Title Children Status

... ... N tickets stage summary

d) Ask the user which epic to work on e) Wait for the user's response before proceeding. Do not auto-select.
Validate epic — Read .bobby/tickets/{ID}*/ticket.md and confirm type: epic. If not an epic, tell the user.
Gather children — Run bobby ticket list --epic {ID} to find all child tickets. If no children exist, tell the user: Create children with: bobby ticket create -t "..." --parent {ID}
Order tickets — Sort children for processing:
- In-progress first: Tickets further along (testing > reviewing > building > planning > backlog) go first — finish what's started
- Then by priority: critical > high > medium > low
- Then by ID: TKT-001 before TKT-002 as tiebreaker
Present the plan — Show the user the processing order and the two-phase approach. Ask for confirmation before starting:

Feature: {epic title} Branch: feature/{epicId}-{slug} Phase 1: Plan {N} ticket(s) holistically Phase 2: Build → Review → Test each sequentially

Order Ticket Title Priority Current Stage

1 ... ... ... ...
Branch guard — This workflow runs in an isolated worktree, so the working directory is clean. Run git branch --show-current. If on main/master, create the feature branch: git checkout -b feature/{epicId}-{slug}. NEVER commit directly to main/master. All child ticket work goes on this single branch.

Epic	Title	Children	Status
...	...	N tickets	stage summary

Order	Ticket	Title	Priority	Current Stage
1	...	...	...	...

Read the full file on GitHub · 200 lines

Files

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.

Changes

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 · 200 lines · 77 tokens per session scan A 44d0aa811809

Subscribe to this mod's changes

run-feature is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 2,807 once invoked, about $0.0003 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.

Claude Code Git and workflow Project management agents ai cli developer-tools npm

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.

AtomicBot-ai/atomic-agent · 48 tokens

hatch3r-board-shared

Shared context and procedures for all board commands. Provides platform-agnostic board config, label taxonomy, branch conventions, sync enforcement, and tooling directives. Platform-specific details are in commands/board/shared-{platform}.md.

hatch3r/hatch3r · 52 tokens

hatch3r-issue-workflow

Guides the 8-step agentic development workflow for issues/work items. Covers parsing issues, loading skills, reading specs, planning, implementing, testing, opening PRs/MRs, and addressing review. Use when working on any issue/work item or when the user mentions an issue number.

hatch3r/hatch3r · 67 tokens

run-feature