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.
curl -O https://raw.githubusercontent.com/marcoguillermaz/Tierward/main/.claude/skills/external-review/SKILL.mdgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/external-review)<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.
<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>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 | $0.00091 | $0.01611 |
| Opus 5 | $0.00046 | $0.00805 |
| Sonnet 5 | $0.00018 | $0.00322 |
| Haiku 4.5 | $0.00009 | $0.00161 |
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.
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) viascripts/external-review.mjs. Cost: ~$0.50–2, ~5 minutes. Use at milestones (v2.0, every 4–6 minor releases, before strategic pivots).
Why two modes
Cross-LLM catches two distinct blind-spot classes: (a) memory-isolation / fresh-eyes — replaceable by a Claude subagent with no transcript context — and (b) architectural diversity from different model families and training corpora. quick covers (a) cheaply on every release; full adds (b) at milestone gates. Running full weekly is wasteful redundancy.
Configuration
- Prompt source:
docs/reviews/external-review-prompt.md(single living file, frontmatterversion:synced to current Tierward release) - Bundle script:
scripts/external-review-bundle.mjs(auto-curated: README + CHANGELOG slice + 1 SKILL sample + Tier-M pipeline + roadmap-status) - Cross-LLM script:
scripts/external-review.mjs(existing, providers via env keys) - Output base:
docs/reviews/<YYYY-MM-DD>-<mode>/(committed; cite in PRs and roadmap entries)
Steps
Step 0 — Parse arguments
Parse --mode (default quick) and --focus (default general). Accepted modes: quick, full. Accepted focus tokens: general, architecture, competitive-position, team-adoption, pricing, enterprise-readiness. Unknown focus is allowed — it gets passed through verbatim to the prompt.
Step 1 — Resolve run directory
Compute RUN_DIR=docs/reviews/$(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.
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.
- 11d ago First seen · 141 lines · 91 tokens per session scan A b58d6a03bb45
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.
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.
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.
build-feature
Full pipeline: evaluation -> spec -> implementation -> review -> QA.
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.
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…
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.