squadai: Skill for Claude Code

.claude/skills/shared/squadai-init-playbook/SKILL.md

squadai-init-playbook is a skill for Claude Code from PedroMosquera/squadai. It costs 49 tokens per session (2,600 once invoked), scanned A, original, MIT.

A detailed procedure guide for the repository-instruction refinement routine. It explains how to collect project signals, identify the working method, check consistency, handle reruns, and write proposed changes.

In plain words
What is it for?
Use it with the repository refinement command. It helps compare the declared methodology with evidence in the repository, gather relevant signals, and follow the required refinement and review steps.
Why use it?
Refining agent instructions requires more than reading a few files; the project may follow test-driven development, specification-driven development, or another method. This guide provides the checks needed to avoid tuning instructions incorrectly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

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/shared/squadai-init-playbook/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 squadai-init-playbook

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pedromosquera/squadai/squadai-init-playbook"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/squadai-init-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,600 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 $0.00049 $0.02600
Opus 5 $0.00024 $0.01300
Sonnet 5 $0.00010 $0.00520
Haiku 4.5 $0.00005 $0.00260

Measured 12d ago against content hash 3d9290976104, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

squadai-init-playbook 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/shared/squadai-init-playbook/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/squadai-init Playbook

Detailed procedures for each /squadai-init phase. The driver command defines the phase order and hard rules; this playbook holds the full procedure per phase.

Phase: Methodology fingerprinting (first run + when project.json changed)

Confirm the methodology in project.json matches what the repo actually practices — misidentifying it produces wrong advice.

Signal Suggests
specs/ or openspec/ directory with markdown specs SDD
Most source files have a paired *_test.{ext} (≥ 50% pairing) TDD
Commits show test:/feat:/refactor: triplets per feature TDD
Neither; commits are by feature, no spec discipline Conventional

If the fingerprint disagrees with project.json.methodology, surface:

Project.json says methodology=<X>, but the repo looks more like <Y>
(<reason>). Continue refining as <X>, or fix project.json first?
[c]ontinue / [a]bort

Default abort — never silently refine for the wrong methodology.

Phase: Repo signal collection

Read in order, stopping early when a signal yields nothing new:

  1. Language manifest(s) matching meta.language/meta.languages — Go: go.mod (+ go.sum tail); Node/TS: package.json (scripts + dependencies); Python: pyproject.toml/setup.py/requirements.txt; Rust: Cargo.toml; Java/Kotlin: pom.xml/build.gradle.kts; Ruby: Gemfile (+ lock tail); PHP: composer.json; otherwise skip and sample source instead.

  2. Top-level layout — depth-2 directory structure (Glob * and */*, else find -maxdepth 2).

  3. CLAUDE.md / AGENTS.md — read in full if present.

  4. Representative files (structured sampling) — pick at most one per row, in order, skipping rows that don't apply:

    Slot What to pick How
    Entry-point main.go, cmd/*/main.go, index.ts, src/index.*, __init__.py, app/main.py, Application.java, cli.py first match
    Most-recently-modified source non-test source changed in last 5 commits git log + git show --name-only
    Representative test file longest test file by LOC (cap 5 KB read) find by test-name patterns
    Error-handling exemplar one file exercising the language's error idiom grep for Error|panic|throw|raise
    Config / build script Makefile, package.json scripts, pyproject.toml [tool.*], Cargo.toml [bin] whichever exists
    Docs entry point README.md, docs/index.* first 100 lines only

Read the full file on GitHub · 248 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 · 248 lines · 49 tokens per session scan A 3d9290976104

Subscribe to this mod's changes

squadai-init-playbook is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 2,600 once invoked, about $0.0002 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

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

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

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