review-tool

review-tool is a command for Claude Code from dzivkovi/agentic-marketing. It costs 18 tokens per session (664 once invoked), scanned A, original, Apache-2.0.

A command that reviews a tool or product using a defined framework covering its skill gaps, architecture, and fit for agent-driven work.

In plain words
What is it for?
Use it to research a named tool, consult its documentation and related runtime or community sources, compare alternatives when needed, and save a review as a Markdown file.
Why use it?
It structures tool research so important evidence, alternatives, and conclusions are recorded consistently.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md.

Good fit Use it to research a named tool, consult its documentation and related runtime or community sources, compare alternatives when needed, and save a review as a Markdown file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dzivkovi/agentic-marketing/review-tool
Install

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.

Clone the repo
git clone --depth 1 https://github.com/dzivkovi/agentic-marketing

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 review-tool

README.md
[![agentmods](https://agentmods.dev/badge/commands/dzivkovi/agentic-marketing/review-tool.svg)](https://agentmods.dev/commands/dzivkovi/agentic-marketing/review-tool)
Your own site
<a href="https://agentmods.dev/commands/dzivkovi/agentic-marketing/review-tool"><img src="https://agentmods.dev/badge/commands/dzivkovi/agentic-marketing/review-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 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 $0.00018 $0.00664
Opus 5 $0.00009 $0.00332
Sonnet 5 $0.00004 $0.00133
Haiku 4.5 $0.00002 $0.00066

Measured 7d ago against content hash 2b93032047a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-tool 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 7d 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/commands/review-tool.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a tool against the Agentic Marketing Anatomy

Execute the tool-review procedure at specs/tool-review.md (current version) on the following target:

Target: $ARGUMENTS

If $ARGUMENTS is empty or ambiguous, ask the user which tool they want reviewed and what URL or canonical name identifies it.

Execution

Follow the procedure's 5 legs in order:

  1. Leg 1 — Internal check (mandatory first)
  2. Leg 2 — Tool docs (use the procedure's routing heuristics: EXA-first for big vendors, Context7 for libraries, gh for GitHub)
  3. Leg 3 — Wrapper / runtime search (Leg 3a = vendor-official runtime FIRST, then 3b community search, then 3c read-the-body)
  4. Leg 4 — Alternatives (skip for single-tool reviews)
  5. Leg 5 — Synthesis (verdict table per procedure; multi-surface table if vendor spans many surfaces)

Persistence

Save output to work/tool-reviews/<slug>.md using a kebab-case slug derived from the tool name. Include the full verdict table + meta-observations + searches-run audit.

Summary to user

After writing the file, report back concisely (<400 words):

  • 3-state verdict (or multi-surface table if applicable) with any modifiers (tier-gated, thin-skin/thick-core, split-endpoint)
  • Vendor-official runtime finding (MCP / SDK / full agent product / none)
  • Persona-named skill-gap (e.g., "No gap for GTM engineers, Partial for marketing consultants")
  • Category-coverage matrix result (if built): per-verb Anatomy / Vendor Companion / AWESOME coverage with any N or Partial cells named
  • Per-verb coverage gaps (when matrix used): each gap named by verb, no collapsed category absent / category present claims
  • Top 3 surprises or gaps in this repo's coverage (Vendor Companion row missing? Awesome-list entry needed? Curation Log entry warranted?)
  • Graduation recommendation: is the review ready to move from work/tool-reviews/ to research/tool-reviews/ (public)?
  • Telemetry: tool-call count + wall time

Read the full file on GitHub · 53 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. 7d ago First seen · 53 lines · 18 tokens per session scan A 2b93032047a4

Subscribe to this mod's changes

review-tool is a command published in the GitHub repository dzivkovi/agentic-marketing (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 664 once invoked, about $0.0001 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.