squadai: Skill for Claude Code

.claude/skills/sdd/sdd-apply/SKILL.md

sdd-apply is a skill for Claude Code from PedroMosquera/squadai. It costs 14 tokens per session (557 once invoked), scanned A, original, MIT.

A software implementation workflow for specification-driven development, where code is built from a written description of the required behavior. It emphasizes reading the full specification, defining interfaces, and testing each stated behavior.

In plain words
What is it for?
Use it to implement specified interfaces and behaviors, handle documented edge cases, write validating tests, and report ambiguities or missing requirements.
Why use it?
It reduces accidental changes and prevents developers from silently filling in gaps or adding features that were not requested. It makes unclear requirements visible during implementation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is PedroMosquera/squadai's own configuration. It tells Claude Code how to work on squadai 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 squadai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PedroMosquera/squadai. 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/PedroMosquera/squadai/main/.claude/skills/sdd/sdd-apply/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

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 sdd-apply

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-apply/github.svg)](https://agentmods.dev/skills/pedromosquera/squadai/sdd-apply)
Your own site
<a href="https://agentmods.dev/skills/pedromosquera/squadai/sdd-apply"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-apply/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 sdd-apply

Your own site · 80×15
<a href="https://agentmods.dev/skills/pedromosquera/squadai/sdd-apply"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-apply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 557 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 $0.00014 $0.00557
Opus 5 $0.00007 $0.00279
Sonnet 5 $0.00003 $0.00111
Haiku 4.5 $0.00001 $0.00056

Measured 9d ago against content hash aa349d5b1d96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sdd-apply 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 9d 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/sdd/sdd-apply/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Apply Skill

Implement exactly what the specification says. No more, no less. This skill is used by the Implementer after the Spec Writer and Designer have produced their artifacts.

Core Principle

Your job is to implement what is specified, not to improve the design. If the spec is wrong, report it — do not fix it silently.

Steps

  1. Read the full spec before writing any code: Understand the complete interface contract before starting the first function.

    • Note all invariants and error conditions
    • Mark any ambiguities to report back to the orchestrator
  2. Implement interfaces first: Create types and method stubs before logic.

    • Implement all interface methods (even stubs return placeholder errors)
    • This ensures compilation and enables parallel work by others
    • Run go build ./... after stubs are in place
  3. Implement one spec item at a time: Work through the spec sequentially.

    • Pick one function or behavior from the spec
    • Write a test for it (even in SDD, tests validate spec compliance)
    • Implement it
    • Verify the test passes
  4. Respect the interface contract strictly:

    • Return exactly the error types specified — no substitutions
    • Produce exactly the output format specified
    • Respect all invariants stated in the spec
    • If spec says "side effect X happens", make it happen
  5. Handle all edge cases in the spec:

    • Check the "Edge Case Behavior" table in the spec
    • Each row must be implemented
    • Do not add undocumented behavior
  6. Do not add extras:

    • No logging unless specified
    • No caching unless specified
    • No additional validation beyond what is specified
    • No convenience methods not in the interface
  7. Report spec gaps: If you encounter behavior the spec does not cover:

    • Do not guess — make a conservative implementation (return error)
    • Document the gap explicitly with a // TODO(spec): ... comment
    • Report gaps to the orchestrator before finalizing

Read the full file on GitHub · 73 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. 9d ago First seen · 73 lines · 14 tokens per session scan A aa349d5b1d96

Subscribe to this mod's changes

sdd-apply is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 557 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

harness-engineering

Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.

paladini/harness-score · 55 tokens

reap

Report how much of the context this agent loads is never used - unused skills, MCP servers, subagents, hooks and always-loaded prose - measured from real session transcripts. Use when asked why the context window is full, what is wasting tokens, or what is safe to remove.

thousandflowers/skillreaper · 56 tokens

gap

Measure the loaded-versus-fired gap - what fraction of each category of loaded context is ever actually invoked, and which MCP tools return mostly noise. Use when asked how much of the context is earning its place, or which categories are worst.

thousandflowers/skillreaper · 48 tokens

replay

Find, analyze, and share AI coding sessions with vibe-replay. Use when the user asks for a replay, wants to find a past session, run a session retro, share Cursor/Claude/Codex session context, or attach session context to a PR.

tuo-lei/vibe-replay · 56 tokens

skill-doctor

Use the skill-doctor CLI or UI to inspect and manage AI-agent skills, rules, instructions, MCP resources, and context cost across supported platforms. Trigger when the user asks to scan or audit agent skills, find duplicates or trigger conflicts, investigate unsafe instructions, estimate context-token cost, compare…

evilstar2016/skill-doctor · 103 tokens

skill-doctor-context-optimizer

Interactively keep the skills, MCP servers/tools, and plugins relevant to the user's current task, preview project-local disables for the rest, apply only explicitly confirmed controls through skill-doctor, and report approximate context-token savings. Trigger when the user asks to slim, optimize, prune, or reduce the…

evilstar2016/skill-doctor · 79 tokens