squad: Skill for Claude Code

.copilot/skills/architectural-review/SKILL.md

architectural-review is a skill for Claude Code, Codex from bradygaster/squad. It costs 24 tokens per session (2,077 once invoked), scanned A, original, MIT.

Instructions for reviewing pull requests that change software architecture, including modules, dependencies, exports, abstractions, or broad refactors. They focus on preserving boundaries and the intended direction of dependencies between packages.

In plain words
What is it for?
Reviewing new packages, cross-package imports, API changes, abstractions, dependency updates, and sweeping refactors in the Squad codebase.
Why use it?
They catch structural problems that may compile successfully but make the codebase harder to maintain or create forbidden dependencies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is bradygaster/squad's own configuration. It tells Claude Code and Codex how to work on squad 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 squad configures →

About the project

bradygaster/squad is a tool that creates a human-directed team of AI development agents inside a project repository through GitHub Copilot. Developers use it to delegate work among persistent specialists such as frontend, backend, testing, and lead agents while retaining responsibility for decisions and review. The catalogue entries are the skills, agents, and instructions that define and coordinate those team members.

bradygaster/squad · 3,160 stars · on GitHub · bradygaster.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to bradygaster/squad. 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/bradygaster/squad/dev/.copilot/skills/architectural-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bradygaster/squad

Made for: Claude Code, Codex.

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 architectural-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/bradygaster/squad/architectural-review.svg)](https://agentmods.dev/skills/bradygaster/squad/architectural-review)
Your own site
<a href="https://agentmods.dev/skills/bradygaster/squad/architectural-review"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/architectural-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00024 $0.02077
Opus 5 $0.00012 $0.01038
Sonnet 5 $0.00005 $0.00415
Haiku 4.5 $0.00002 $0.00208

Measured 8d ago against content hash 645dd9d1e283, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

architectural-review scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

The CLI has **protected bootstrap files** that must use ONLY Node.js built-in modules (`node:fs`, `node:path`, `node:child_process`, `node:util`). These files run before the SDK is loaded.
.copilot/skills/architectural-review/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

When reviewing a PR that touches core architecture, the reviewer must verify that structural invariants are preserved. This skill covers reviewing existing PRs for architectural quality — not writing proposals (see architectural-proposals/SKILL.md for that).

Use this skill when a PR includes any of:

  • New modules, packages, or directories
  • Dependency changes (package.json, import additions across package boundaries)
  • API surface changes (new or modified exports from index.ts barrel files)
  • Cross-package imports (anything crossing the SDK/CLI boundary)
  • New abstractions (interfaces, base classes, registries, factories)
  • Sweeping refactors (file renames, pattern migrations, bulk conversions)

Patterns

1. Module Boundary Enforcement

The Squad codebase has two core packages with a strict dependency direction:

squad-cli → depends on → squad-sdk
squad-sdk → NEVER depends on → squad-cli

Check every new import statement in the PR:

  • CLI files may import from SDK (@bradygaster/squad-sdk)
  • SDK files must NEVER import from CLI
  • If a PR adds an SDK import that pulls in CLI code, reject it

2. Zero-Dependency Bootstrap Contract

The CLI has protected bootstrap files that must use ONLY Node.js built-in modules (node:fs, node:path, node:child_process, node:util). These files run before the SDK is loaded.

Protected files (authoritative list from copilot-instructions.md):

File Purpose
packages/squad-cli/src/cli/core/detect-squad-dir.ts Finds .squad/ at startup
packages/squad-cli/src/cli/core/errors.ts Error classes (SquadError, fatal())
packages/squad-cli/src/cli/core/gh-cli.ts GitHub CLI wrapper
packages/squad-cli/src/cli/core/output.ts Color/emoji console output
packages/squad-cli/src/cli/core/history-split.ts Portable knowledge separator

Review checklist for bootstrap files:

  • ❌ No new import or require of anything outside node:*
  • ❌ No conversion to FSStorageProvider, StorageProvider, or SDK abstractions
  • ✅ Look for — zero dependencies markers in file headers
  • ✅ If the PR adds a new bootstrap utility, it must be added to this table and have a zero-dependency regression test

Read the full file on GitHub · 201 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. 8d ago First seen · 201 lines · 24 tokens per session scan A 645dd9d1e283

Subscribe to this mod's changes

architectural-review is a skill published in the GitHub repository bradygaster/squad (3,160 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 2,077 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

ralphctl-code-review-and-quality

Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when you are the evaluator assessing a generator's output, and when reviewing any change before signalling…

lukas-grigis/ralphctl · 76 tokens

dos-verify-done-claims

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.

anthony-chaudhary/dos-kernel · 61 tokens

ponytail-review

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this…

dmae97/omk · 100 tokens

ponytail-audit

Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find…

dmae97/omk · 105 tokens

sdd-tasks

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.

Gentleman-Programming/gentle-ai · 25 tokens

sdd-research

Trigger: SDD research, external evidence, source-backed research. Produce auditable evidence for a selected research lane.

Gentleman-Programming/gentle-ai · 28 tokens