Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/nick-railsback/skill-engine/reviewnpx skills add nick-railsback/skill-engine --skill reviewgit clone --depth 1 https://github.com/nick-railsback/skill-engineWrote 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/nick-railsback/skill-engine/review)<a href="https://agentmods.dev/skills/nick-railsback/skill-engine/review"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/review.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.02229 |
| Opus 5 | $0.00016 | $0.01115 |
| Sonnet 5 | $0.00007 | $0.00446 |
| Haiku 4.5 | $0.00003 | $0.00223 |
Grade A, and why
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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
A pending proposal lives at <install>/<name>-context.proposed/. This skill inspects that staging directory without mutating either it or the live contextualizer at <install>/<name>-context/. The user's review is what teaches the engine what "good" means for this source — review is the surface that loads the question, not a rubber stamp on a pre-committed artifact.
When to invoke
Invoke /skill-engine:review <name> after DISCOVER or REFRESH has surfaced a "Proposal staged at <name>-context.proposed/" line in its post-run summary. The skill runs in two passes against the same proposal: the first pass prints the manifest, the configured diff command, and the path to REVIEW.md; the second pass (after the user fills Step 1 of REVIEW.md) re-reads the file, generates the Step 2 disagreement set, and rewrites that section in place.
Resolving <name>
The <name> argument is the contextualizer slug without the -context suffix. /skill-engine:review vitejs-vite operates on <install>/vitejs-vite-context.proposed/.
Bare invocation (no argument) works when exactly one *-context.proposed/ directory exists under <install>. When zero match, surface no proposed staging dir found under <install> and exit cleanly. When two or more match, surface the list and ask which one (mirrors discover/SKILL.md's "Multiple contextualizers" pattern).
Resolve <install> from the live contextualizer location. The proposed directory always sits as a sibling of the live <name>-context/ directory; <install> is whichever level the live skill is installed at (~/.claude/skills/, ~/.claude/local/skills/, or <repo>/.claude/skills/). Iterate the same three roots using-skill-engine's router walks (see the "Locating the contextualizer root" block in discover/SKILL.md); the first match wins.
First pass — manifest and diff command
When REVIEW.md exists but Step 1 still contains the literal ___ blanks (i.e., the user has not yet filled their predictions), do the following in order:
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.
- 4d ago First seen · 100 lines · 33 tokens per session scan A f5d144cd10a5
review is a skill published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 27d ago), licensed MIT. It adds 33 tokens to every session and 2,229 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
erpaval
Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…
product-discovery
File-first orchestrator for product discovery and spec frameworks. Frames the problem with a Discovery Lead, Product Analyst, or System Architect role. Spawns parallel framework agents (Double Diamond, How Might We, Jobs to Be Done, user stories with INVEST, EARS for AI-coder specs, Gherkin), synthesizes into a PRD or…
agent-ux-patterns
Agent UX patterns and human-in-the-loop design: Twilio A2H protocol, Levels of Autonomy (L0-L5), inbox pattern, progressive trust, decision journal, gate reviews, autonomous work reports. Six-phase methodology from vague pain point to concrete data model via landscape research and multi-direction brainstorming. Use…
meta-prompt-optimizer
Audit and rewrite prompts against Claude Opus 4.7 instruction-following best practices. Produces a scored audit plus a rewritten prompt. Use when the user asks to audit, review, critique, rewrite, improve, optimize, tighten, score, fix, migrate, or draft a prompt — including system prompts, CLAUDE.md files, Claude…
product-strategy
File-first orchestrator for business and product strategy frameworks. Frames the challenge with a CPO / CSO / VP Design role, spawns parallel framework agents (Rumelt kernel + Crux, Wardley Maps, Minto Pyramid as thinking structure, Working Backwards PR-FAQ as discovery artifact), synthesizes outputs into one strategy…
tech-stack-builder
Opinionated tech stack recommendations and settled library references. Two modes: (1) /build-stack runs parallel researcher agents to compare candidates and emit a stack report + ADRs for greenfield projects; (2) direct reference routing for coding with settled defaults. Use when the user asks to recommend a stack…