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.
curl -O https://raw.githubusercontent.com/shep-ai/shep/main/.claude/skills/shep-kit-new-feature-fast/SKILL.mdgit clone --depth 1 https://github.com/shep-ai/shepWrote 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/shep-ai/shep/shep-kit-new-feature-fast)<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.
<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>- 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 | $0.00093 | $0.02647 |
| Opus 5 | $0.00046 | $0.01324 |
| Sonnet 5 | $0.00019 | $0.00529 |
| Haiku 4.5 | $0.00009 | $0.00265 |
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.
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.
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.
- 12d ago First seen · 299 lines · 93 tokens per session scan A 767efbcb7ef3
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.
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…
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…
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.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.
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…