shep: Skill for Claude Code

.claude/skills/shep-kit-fast-loop/SKILL.md

shep-kit:fast-loop is a skill for Claude Code from shep-ai/shep. It costs 79 tokens per session (468 once invoked), scanned A, original, MIT.

A rapid coding mode for making small changes while a development server is running. It skips TDD, which means writing tests before or alongside code, as well as builds and commits during the iteration.

In plain words
What is it for?
Use it for quick, focused edits in applications with hot reload, then run validation and tests after the user says the work is done.
Why use it?
It keeps feedback cycles short when the user wants to inspect changes manually and guide the next adjustment.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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-fast-loop/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:fast-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-fast-loop.svg)](https://agentmods.dev/skills/shep-ai/shep/shep-kit-fast-loop)
Your own site
<a href="https://agentmods.dev/skills/shep-ai/shep/shep-kit-fast-loop"><img src="https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-fast-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 468 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 $0.00079 $0.00468
Opus 5 $0.00039 $0.00234
Sonnet 5 $0.00016 $0.00094
Haiku 4.5 $0.00008 $0.00047

Measured 8d ago against content hash 9fd1b8ac6423, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

shep-kit:fast-loop 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 8d 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-fast-loop/SKILL.md · 50 lines

What it actually says

Fast Loop — Rapid Iteration Mode

Skip TDD, builds, and commits. Just edit code, let the dev server hot-reload, and iterate based on user feedback.

What This Overrides

This skill temporarily suspends these CLAUDE.md mandates for the duration of the session:

  • TDD — no tests required during fast-loop
  • Spec-driven — no spec required, user drives direction
  • Storybook stories — not required during iteration
  • Commit format — no commits until user says "done"

Rules

  1. Edit code only — no pnpm test, no pnpm build, no git commit
  2. Small, focused changes — one thing at a time so the user can verify each step
  3. Trust the dev server — assume hot-reload picks up changes (Next.js, Vite, etc.)
  4. Wait for user feedback — after each change, pause and let the user check the result
  5. No over-engineering — do exactly what the user asks, nothing more
  6. When user says "done" — remind them to run pnpm validate and tests before committing

Flow

User describes change → Edit files → User checks dev server → Repeat

Exit

When the user is satisfied, suggest:

pnpm validate        # lint + format + typecheck
pnpm test:unit       # catch regressions

Then offer /shep-kit:commit-pr or /commit to wrap up.

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. 8d ago First seen · 50 lines · 79 tokens per session scan A 9fd1b8ac6423

Subscribe to this mod's changes

shep-kit:fast-loop is a skill published in the GitHub repository shep-ai/shep (248 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 468 once invoked, about $0.0004 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

nft-standards

Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.

wshobson/agents · 48 tokens

cost-optimization

Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

wshobson/agents · 48 tokens

istio-traffic-management

Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.

wshobson/agents · 40 tokens

postgresql-table-design

Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.

wshobson/agents · 37 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens