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.
curl -O https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/skills/shared/squadai-init-playbook/SKILL.mdgit clone --depth 1 https://github.com/PedroMosquera/squadaiWrote 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/pedromosquera/squadai/squadai-init-playbook)<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.
<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>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 | $0.00049 | $0.02600 |
| Opus 5 | $0.00024 | $0.01300 |
| Sonnet 5 | $0.00010 | $0.00520 |
| Haiku 4.5 | $0.00005 | $0.00260 |
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.
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:
-
Language manifest(s) matching
meta.language/meta.languages— Go:go.mod(+go.sumtail); 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. -
Top-level layout — depth-2 directory structure (Glob
*and*/*, elsefind -maxdepth 2). -
CLAUDE.md / AGENTS.md — read in full if present.
-
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.pyfirst match Most-recently-modified source non-test source changed in last 5 commits git log+git show --name-onlyRepresentative test file longest test file by LOC (cap 5 KB read) findby test-name patternsError-handling exemplar one file exercising the language's error idiom grep for Error|panic|throw|raiseConfig / build script Makefile,package.jsonscripts,pyproject.toml [tool.*],Cargo.toml [bin]whichever exists Docs entry point README.md,docs/index.*first 100 lines only
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 · 248 lines · 49 tokens per session scan A 3d9290976104
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.
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.
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.
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.
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.
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…
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…