claude-scaffold: Skill for Claude Code

.claude/skills/critical-analysis/SKILL.md

critical-analysis is a skill for Claude Code from pyramidheadshark/claude-scaffold. It costs 0 tokens per session (1,720 once invoked), scanned A, original, MIT.

A structured critique system for machine-learning experiments and software architecture decisions. It uses several review roles to examine risks, assumptions, and design quality before work begins.

In plain words
What is it for?
Use it to review new integrations, refactors, infrastructure changes, machine-learning experiment plans, and choices that lack prior testing.
Why use it?
It helps expose problems in architecture, infrastructure changes, experiments, and parameter choices before implementation. It also checks whether an architecture decision is grounded in a design document.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is pyramidheadshark/claude-scaffold's own configuration. It tells Claude Code how to work on claude-scaffold 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 claude-scaffold configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pyramidheadshark/claude-scaffold. 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/pyramidheadshark/claude-scaffold/main/.claude/skills/critical-analysis/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pyramidheadshark/claude-scaffold

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 critical-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/pyramidheadshark/claude-scaffold/critical-analysis/github.svg)](https://agentmods.dev/skills/pyramidheadshark/claude-scaffold/critical-analysis)
Your own site
<a href="https://agentmods.dev/skills/pyramidheadshark/claude-scaffold/critical-analysis"><img src="https://agentmods.dev/badge/skills/pyramidheadshark/claude-scaffold/critical-analysis/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 critical-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/pyramidheadshark/claude-scaffold/critical-analysis"><img src="https://agentmods.dev/badge/skills/pyramidheadshark/claude-scaffold/critical-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,720 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 $0.00000 $0.01720
Opus 5 $0.00000 $0.00860
Sonnet 5 $0.00000 $0.00344
Haiku 4.5 $0.00000 $0.00172

Measured 10d ago against content hash db47aee098e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

critical-analysis 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 10d 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/critical-analysis/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Critical Analysis (v1.1)

Multi-role critique system for ML experiments and architecture decisions. Based on: Solo Performance Prompting (NAACL 2024), CrewAI role taxonomy, Bermingham 13-agent DA-as-gate, De Bono Six Thinking Hats (Black Hat gating).


When to Load (Auto-Default Behavior)

Before any of the following — run Quick Mode without waiting for user request:

  • Architecture or design decision (new integration, refactor, layer change)
  • ML experiment launch (clustering, training run, hyperparameter search)
  • Infrastructure change (Terraform, Docker, secrets, permissions)
  • Parameter choice without prior ablation

Design doc check: for any architectural decision, verify design-doc.md exists and guides this decision. If missing → [DA]: "No design doc — decisions are ungrounded."

Quick Mode: if all 8 roles return "clear" — proceed. If any role flags CRITICAL — surface it to the user before proceeding.

This is NOT optional. Critique runs before code, not after.


8-Role Taxonomy

Role Source Key Question
[Security] Security Sentinel CrewAI Code Security Auditor Injection, auth, secrets, attack surface — what can be exploited?
[Perf] Performance Analyst CrewAI Performance Optimizer O(n²), wasted iterations, memory — where is 80% of cost wasted?
[DA] Devil's Advocate Bermingham 13-agent + Black Hat What is the strongest argument AGAINST this? What breaks in 90 days?
[Crutch] Crutch Identifier Project history: defectoscopy + hub Is this a reusable pattern or a workaround being institutionalized?
[Strategy] Strategic Horizon DX/tech debt, 6-month view New external dep / >3 files / new interface contract? Flag only if yes.
[ML] ML Experiment Auditor arxiv 2603.15916, project history Are we at a plateau? Is this experiment worth running at all?
[TestCov] Testing Coverage Qodo/CodeRabbit/Anthropic tool Does this change need new tests? Are edge cases covered?
[Obs] Observability Enforcer Google SRE, OpenTelemetry practices Can we debug this in prod? Are logs/metrics/traces in place?

Read the full file on GitHub · 162 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 162 lines · 0 tokens per session scan A db47aee098e1

Subscribe to this mod's changes

critical-analysis is a skill published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,720 tokens. 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

mle-workflow

Production ML engineering workflow — data contracts, reproducible training, evaluation gates, deployment, and monitoring. Use when building, reviewing, or hardening ML systems beyond notebooks.

chandrudp29/skillhub · 39 tokens

data-scientist

!cat Claude-Production-Grade-Suite/.protocols/ux-protocol.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/input-validation.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/tool-efficiency.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/visual-identity.md…

nagisanzenin/production-grade · 43 tokens

ai-engineer

Builds production AI/ML systems — model training, fine-tuning, MLOps pipelines, model serving, evaluation frameworks, RAG optimization, and agent orchestration at scale. Use when the user asks to build, train, or deploy ML models, set up MLOps pipelines, optimize RAG systems, create inference endpoints, or design…

buiphucminhtam/forgewright · 78 tokens

data-scientist

!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults".

buiphucminhtam/forgewright · 52 tokens

ai-ml-engineering

AI/ML Engineering Review: Reviews AI/ML systems for production readiness — model serving, MLOps pipelines, LLM integration patterns, prompt engineering, evaluation frameworks, and responsible AI. Covers model deployment, feature stores, experiment tracking, monitoring/drift detection, and AI safety. Use when the user…

camilooscargbaptista/cto-toolkit · 112 tokens

git-hooks-manager

Setup and manage git hooks for pre-commit, pre-push automation (lint, test, format).

glincker/claude-code-marketplace · 25 tokens