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 commands/tommymorgan/claude-plugins/review-featuresgit clone --depth 1 https://github.com/tommymorgan/claude-pluginsWrote 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/commands/tommymorgan/claude-plugins/review-features)<a href="https://agentmods.dev/commands/tommymorgan/claude-plugins/review-features"><img src="https://agentmods.dev/badge/commands/tommymorgan/claude-plugins/review-features.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 | $0.00019 | $0.01542 |
| Opus 5 | $0.00010 | $0.00771 |
| Sonnet 5 | $0.00004 | $0.00308 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
tommymorgan:review-features 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Features with Expert Panel
Review any Gherkin scenarios using a panel of domain experts. Accepts feature files, plan files, directories, or glob patterns.
Workflow
Step 1: Detect Input Type and Load Scenarios
Parse the argument to determine input type:
$ARGUMENTS
Input detection:
- Ends in
.feature→ single feature file - Ends in
.md→ plan file (extract Gherkin scenarios) - Is a directory (no extension, exists as dir) → all
.featurefiles in directory - Contains
*→ glob pattern for.featurefiles
If no argument provided:
- Check for
features/directory in current project - If exists, use
features/*.feature - Otherwise, error: "No input provided. Specify a .feature file, plan file, directory, or glob pattern."
Load scenarios based on input type:
For .feature files:
- Read file content
- Extract all
Scenario:andScenario Outline:blocks - Preserve Feature context (Feature name, Background if present)
For .md plan files:
- Read file content
- Extract Gherkin scenarios from User Requirements and Technical Specifications sections
- Scenarios are blocks starting with
Scenario:after<!-- TODO -->or<!-- DONE -->markers
For directories:
- Find all
.featurefiles in directory (non-recursive) - Load scenarios from each file
For glob patterns:
- Expand glob to matching
.featurefiles - Load scenarios from each file
Step 2: Detect Context from Content
Scan scenario content for keywords to categorize the context:
Keywords → Categories:
api, endpoint, http, rest, jwt, request, response→ backend_servicehook, bash, cli, git, pre-push, pre-commit, shell→ hookweb, ui, page, component, dashboard, form, button, click→ ui_componentdatabase, schema, migration, table, postgres, sql, query→ database_migrationplugin, command, skill, agent, claude→ claude_plugin
Content may have multiple categories.
Store detected categories - experts will use this to filter relevance.
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 · 236 lines · 19 tokens per session scan A 96c485fda2b5
tommymorgan:review-features is a command published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,542 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.
Other commands, from other repositories
playwright
Write or update Playwright E2E tests following project conventions.
e2e
使用 Playwright 对 Web UI 进行端到端测试(支持视频录制、Trace 录制、控制台/网络日志捕获).
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
plan-spec
仅在人工明确安排 UI 自动化时,根据任务、产品规则或原型生成独立行为 Spec.