shep: Skill for Claude Code

.claude/skills/shep-kit-new-feature-fast/SKILL.md

shep-kit:new-feature-fast is a skill for Claude Code from shep-ai/shep. It costs 93 tokens per session (2,647 once invoked), scanned A, original, MIT.

A fast feature-specification workflow that combines feature definition, technical research, and implementation planning in one pass. It creates YAML files describing the feature, research, plan, tasks, and status.

In plain words
What is it for?
Use it for well-understood features when you want inferred naming, limited clarification, technical decisions, architecture, and task breakdown produced together.
Why use it?
It shortens the path from a clear feature idea to an implementation-ready set of documents. It is less suitable when the feature is ambiguous or needs deep library evaluation.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

This is shep-ai/shep's own configuration. It tells Claude Code how to work on shep itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shep configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shep-ai/shep. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shep-ai/shep/main/.claude/skills/shep-kit-new-feature-fast/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/shep-ai/shep

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.

agentmods badge for shep-kit:new-feature-fast

README.md
[![agentmods](https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-new-feature-fast/github.svg)](https://agentmods.dev/skills/shep-ai/shep/shep-kit-new-feature-fast)
Your own site
<a href="https://agentmods.dev/skills/shep-ai/shep/shep-kit-new-feature-fast"><img src="https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-new-feature-fast/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.

agentmods 80×15 button for shep-kit:new-feature-fast

Your own site · 80×15
<a href="https://agentmods.dev/skills/shep-ai/shep/shep-kit-new-feature-fast"><img src="https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-new-feature-fast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,647 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.02647
Opus 5 $0.00046 $0.01324
Sonnet 5 $0.00019 $0.00529
Haiku 4.5 $0.00009 $0.00265

Measured 12d ago against content hash 767efbcb7ef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

shep-kit:new-feature-fast 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 12d 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/shep-kit-new-feature-fast/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fast-Track Feature Specification

Collapse the full new-feature → research → plan pipeline into a single autonomous pass. Produces all the same YAML artifacts as the full pipeline but with minimal user interaction (0-2 clarifying questions max).

Full workflow guide: docs/development/spec-driven-workflow.md

When to Use

  • Feature scope is well-understood from the one-liner description
  • You want to skip the multi-step interactive flow
  • You want to get to implementation quickly

When NOT to Use

  • Highly ambiguous features requiring extensive discovery
  • Features with many open questions or unknowns
  • When you specifically need deep library evaluation with benchmarks

Input

The user provides a feature description inline:

/shep-kit:new-feature-fast add unit tests to backend services

If no description is provided, ask for a one-liner description. That is the only mandatory question.

Workflow

Phase 1: Scaffold

1.1 Derive Feature Name

Extract a kebab-case feature name from the user's description. Do NOT ask — infer it.

Examples:

  • "add unit tests to backend" → backend-unit-tests
  • "implement dark mode toggle" → dark-mode-toggle
  • "fix memory leak in agent runner" → agent-runner-memory-fix
1.2 Create Branch & Directory
# Determine next spec number
NEXT_NUM=$(ls -d specs/[0-9][0-9][0-9]-* 2>/dev/null | sort | tail -1 | grep -oP '^\d{3}' | xargs -I{} printf "%03d" $(({} + 1)))
# If no specs exist, use 001
[ -z "$NEXT_NUM" ] && NEXT_NUM="001"

FEATURE_NAME="<derived-kebab-case>"

# Create branch from main
git checkout main && git pull
git checkout -b "feat/${NEXT_NUM}-${FEATURE_NAME}"

# Run scaffolding (creates all template files)
.claude/skills/shep-kit-new-feature/scripts/init-feature.sh "$NEXT_NUM" "$FEATURE_NAME"

This reuses the existing init script — same templates, same directory structure.

Phase 2: Deep Analysis (Silent)

Before writing any YAML, perform thorough codebase analysis. This is the foundation for ALL subsequent YAML files. Do NOT show analysis to user — go straight to writing.

Read the full file on GitHub · 299 lines

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.

  1. 12d ago First seen · 299 lines · 93 tokens per session scan A 767efbcb7ef3

Subscribe to this mod's changes

shep-kit:new-feature-fast is a skill published in the GitHub repository shep-ai/shep (250 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 2,647 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

saga-orchestration

Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…

wshobson/agents · 91 tokens

task-coordination-strategies

Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.

wshobson/agents · 49 tokens

bazel-build-optimization

Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.

wshobson/agents · 36 tokens

nx-workspace-patterns

Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.

wshobson/agents · 35 tokens

context-driven-development

Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when…

wshobson/agents · 103 tokens