Tierward: Skill for Claude Code

.claude/skills/external-review/SKILL.md

external-review is a skill for Claude Code from marcoguillermaz/Tierward. It costs 91 tokens per session (1,611 once invoked), scanned A, original, MIT.

A release-review workflow that sends a bundled snapshot of the Tierward project to one or more AI models for a fresh assessment.

In plain words
What is it for?
Use it for release sanity checks, milestone reviews, and checking architectural changes before publication.
Why use it?
It provides an outside check without the reviewers relying on the project's existing conversation or memory. The quick mode gives one review, while the full mode compares several model families.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents; positional $N argument.

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/external-review.mjs \.

Part of the tierward plugin — 29 skills, 1 command, 1 hook, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to marcoguillermaz/Tierward. 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/marcoguillermaz/Tierward/main/.claude/skills/external-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/marcoguillermaz/Tierward

Made for: Claude Code.

Or install tierward, the plugin that ships this one along with the rest of its 29 skills, 1 command, 1 hook, 1 MCP server.

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 external-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcoguillermaz/tierward/external-review/github.svg)](https://agentmods.dev/skills/marcoguillermaz/tierward/external-review)
Your own site
<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/external-review"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/external-review/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 external-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/external-review"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/external-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 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 $0.00091 $0.01611
Opus 5 $0.00046 $0.00805
Sonnet 5 $0.00018 $0.00322
Haiku 4.5 $0.00009 $0.00161

Measured 11d ago against content hash b58d6a03bb45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

external-review 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 11d 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/external-review/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

external-review

Pre-release sanity pass for Tierward. Two modes:

  • --mode=quick (default) — single fresh-context Claude review. Cost: ~$0.10, ~60 seconds. Use on every release.
  • --mode=full — cross-LLM (GPT-4.1 / Gemini 2.5 Pro / Mistral Large / Perplexity Sonar Pro) via scripts/external-review.mjs. Cost: ~$0.50–2, ~5 minutes. Use at milestones (v2.0, every 4–6 minor releases, before strategic pivots).

Why two modes

Cross-LLM catches two distinct blind-spot classes: (a) memory-isolation / fresh-eyes — replaceable by a Claude subagent with no transcript context — and (b) architectural diversity from different model families and training corpora. quick covers (a) cheaply on every release; full adds (b) at milestone gates. Running full weekly is wasteful redundancy.

Configuration

  • Prompt source: docs/reviews/external-review-prompt.md (single living file, frontmatter version: synced to current Tierward release)
  • Bundle script: scripts/external-review-bundle.mjs (auto-curated: README + CHANGELOG slice + 1 SKILL sample + Tier-M pipeline + roadmap-status)
  • Cross-LLM script: scripts/external-review.mjs (existing, providers via env keys)
  • Output base: docs/reviews/<YYYY-MM-DD>-<mode>/ (committed; cite in PRs and roadmap entries)

Steps

Step 0 — Parse arguments

Parse --mode (default quick) and --focus (default general). Accepted modes: quick, full. Accepted focus tokens: general, architecture, competitive-position, team-adoption, pricing, enterprise-readiness. Unknown focus is allowed — it gets passed through verbatim to the prompt.

Step 1 — Resolve run directory

Compute RUN_DIR=docs/reviews/$(date -u +%Y-%m-%d)-<mode>/. If it already exists, append -<n> until unique. Create RUN_DIR/bundle/ and RUN_DIR/responses/.

Step 2 — Verify prompt freshness

Read frontmatter of docs/reviews/external-review-prompt.md. If version does not match the current Tierward release (read from packages/cli/package.json), STOP and print: "Prompt is stale (prompt={X}, Tierward={Y}). Update docs/reviews/external-review-prompt.md frontmatter and content before running." Do NOT auto-update — the prompt body has Tierward-state numbers that need a human review.

Read the full file on GitHub · 141 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. 11d ago First seen · 141 lines · 91 tokens per session scan A b58d6a03bb45

Subscribe to this mod's changes

external-review is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 1,611 once invoked, about $0.0005 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

address-conductor-comment

A workflow for handling pending Conductor code-review comments, including reading their discussion and assigning changes to subagents when appropriate.

S-Nakamur-a/conductor · 32 tokens

explain-comment

A skill that reads a specified file or code range and adds explanatory comments in Japanese. The comments use a question style and focus on important logic, design choices, and side effects.

S-Nakamur-a/conductor · 37 tokens

build-feature

Full pipeline: evaluation -> spec -> implementation -> review -> QA.

Guild-Agents/guild · 15 tokens

cn-check

Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.

continuedev/continue · 49 tokens

solid-principles

SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…

decebals/claude-code-java · 73 tokens

architecture-review

Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering. Use when user asks "review architecture", "check structure", "package organization", or when evaluating if a codebase follows clean architecture principles.

decebals/claude-code-java · 51 tokens