mcp-tui: Skill for Claude Code

.claude/skills/implement-slice/SKILL.md

implement-slice is a skill for Claude Code from standardbeagle/mcp-tui. It costs 70 tokens per session (1,355 once invoked), scanned A, original, MIT.

A guide for implementing features as vertical slices with test-driven development (TDD), where tests are written before the code and development follows failing, passing, and cleanup steps.

In plain words
What is it for?
Use it to build features with an end-to-end smoke test, then add the validation, logic, data, API, and user-interface work needed to make that test pass.
Why use it?
It keeps each change focused on a complete user outcome and checks the feature from the outside through its layers.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is standardbeagle/mcp-tui's own configuration. It tells Claude Code how to work on mcp-tui 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 mcp-tui configures →

Reuse

Borrowing it

Nothing to install: this file belongs to standardbeagle/mcp-tui. 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/standardbeagle/mcp-tui/main/.claude/skills/implement-slice/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/standardbeagle/mcp-tui

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 implement-slice

README.md
[![agentmods](https://agentmods.dev/badge/skills/standardbeagle/mcp-tui/implement-slice/github.svg)](https://agentmods.dev/skills/standardbeagle/mcp-tui/implement-slice)
Your own site
<a href="https://agentmods.dev/skills/standardbeagle/mcp-tui/implement-slice"><img src="https://agentmods.dev/badge/skills/standardbeagle/mcp-tui/implement-slice/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 implement-slice

Your own site · 80×15
<a href="https://agentmods.dev/skills/standardbeagle/mcp-tui/implement-slice"><img src="https://agentmods.dev/badge/skills/standardbeagle/mcp-tui/implement-slice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01355
Opus 5.5 $0.00028 $0.00542
Sonnet 5.5 $0.00014 $0.00271
Haiku 4.5 $0.00007 $0.00136

Measured 1mo ago against content hash 20084e27a28f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

implement-slice 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/implement-slice/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Vertical Slice (TDD)

Implement a feature as a complete vertical slice using strict RED/GREEN/REFACTOR discipline. Each slice delivers working functionality through all layers — not a horizontal layer across features.

Pre-Flight Checks

Before writing any code:

  1. Confirm the feature scope and acceptance criteria with the user
  2. Read .claude/rules/architecture.md for active patterns and constraints
  3. Read .claude/rules/tdd.md for TDD discipline rules
  4. Identify which layers this slice touches (validation, logic, data, API, UI)
  5. Verify the feature is small enough for one vertical slice (if not, split first)

Step 1 -- Write the Smoke Test (RED)

Write one end-to-end smoke test for the core user journey at HIGHEST fidelity.

Smoke Test Rules

  • Full e2e — real UI (if applicable), real backend, real database
  • NO mocks, stubs, or simulations
  • Test the complete user journey from entry to exit
  • Run it — it MUST FAIL (RED) because the feature doesn't exist yet
# Example: "User can create a post"
test("user creates a post and sees it in the list"):
  navigate to /posts/new
  fill in title and body
  click submit
  assert redirected to /posts
  assert new post appears in list

Run with: go test (CLI subprocess + live MCP servers: npx server-everything, test-servers/*.js)

Commit: RED: Smoke test for [feature]

Step 2 -- Identify the Thinnest Slice

Break the feature into the smallest possible behavior increments. Each increment is ONE RED/GREEN/REFACTOR cycle.

Slice Planning

List the behaviors in implementation order (dependencies first):

Example for "User can create a post":
  1. Post validation rejects empty title (pure logic)
  2. Post can be persisted to database (data layer)
  3. API endpoint accepts POST /posts (API layer)
  4. UI form submits to API (presentation layer)
  5. Success redirects to post list (navigation)

Each behavior becomes one TDD cycle. Order matters — build from the inside out, but always as a vertical slice (not all validation first, then all data, then all API).

Read the full file on GitHub · 174 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. 1mo ago First seen · 174 lines · 70 tokens per session scan A 20084e27a28f

Subscribe to this mod's changes

implement-slice is a skill published in the GitHub repository standardbeagle/mcp-tui (12 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 1,355 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 2026-09-28.

Related

Other skills, from other repositories

implement

Implement a technical design by decomposing it into dependency-ordered vertical slices, executing each with TDD red-green, reviewing each via an isolated sub-agent, and persisting progress to a state file so work survives session restarts. Use when the user has a tech design (doc or settled conversation) and says…

open-octo/octo-agent · 97 tokens

agent-e2e-test-specialist

Specialist subagent: Playwright, Cypress, and visual regression testing specialist. Use only when the user explicitly asks for E2E tests, browser test automation, or visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.

travisjneuman/.claude · 76 tokens

testing

TDD/BDD testing principles. Use when writing tests, reviewing test coverage, setting up testing, or discussing test strategy and test architecture.

TheBeardedBearSAS/claude-craft · 30 tokens

cypress-ops

Cypress end-to-end and component testing operations - selector/retry-ability strategy, cy.intercept network stubbing, cy.session auth, component vs e2e, flake diagnosis, CI, Test Replay. Use for: cypress, e2e test, component test, cy.get, cy.intercept, cy.session, data-cy, data-test, retry-ability, flake, flaky test…

0xDarkMatter/claude-mods · 104 tokens

playwright-ops

Playwright end-to-end testing operations - selectors, fixtures, network mocking, auth, parallelism, CI, visual regression, flake hunting. Use for: playwright, e2e test, end-to-end testing, browser test, getByRole, page object, storageState, trace viewer, flaky test, test sharding, visual regression, toHaveScreenshot…

0xDarkMatter/claude-mods · 85 tokens

refactor-ops

Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function, god object, feature envy, DRY…

0xDarkMatter/claude-mods · 95 tokens