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.
git clone --depth 1 https://github.com/davistroy/claude-marketplaceWrote 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/davistroy/claude-marketplace/scaffold-plugin.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/scaffold-plugin.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/scaffold-plugin.eval/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/commands/davistroy/claude-marketplace/scaffold-plugin.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/scaffold-plugin.eval.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 | $0.00000 | $0.00590 |
| Opus 5 | $0.00000 | $0.00295 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade C, and why
scaffold-plugin.eval scanned grade C with 1 finding 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf plugins/test-plugin plugins/analytics-plugin How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /scaffold-plugin
Purpose
Creates a new plugin with the proper directory structure, metadata files, and starter files. Good output: a complete, valid plugin skeleton that passes /validate-plugin immediately after creation.
Fixtures
None — generates directory structure in the marketplace repo.
Setup
Run on a feature branch to avoid polluting main with test plugins.
Test Scenarios
S1: Happy path — scaffold a new plugin
Invocation: /scaffold-plugin (then answer prompts)
Interaction:
- Plugin name:
test-plugin - Description:
Test plugin for eval purposes
Must:
- Creates
plugins/test-plugin/directory - Creates
plugins/test-plugin/.claude-plugin/plugin.jsonwith correct metadata - Creates
plugins/test-plugin/commands/directory - Creates
plugins/test-plugin/skills/directory - plugin.json has
name,version,descriptionfields - Registers the new plugin in
.claude-plugin/marketplace.json
Should:
- Creates a starter command file with placeholder content
- Creates a
references/directory - Reports which files were created
Must NOT:
- Create files with invalid JSON (plugin.json must be valid)
- Skip registering in marketplace.json
- Use a flat skill file (
skills/help.md) instead of nested structure
S2: Validate scaffold immediately
After S1, run:
Invocation: /validate-plugin test-plugin
Must:
- Plugin passes all structural validation checks
- No "missing required file" errors
S3: Plugin name as argument
Invocation: /scaffold-plugin analytics-plugin
Must:
- Uses
analytics-pluginwithout prompting for name - Creates
plugins/analytics-plugin/with all required files
S4: Error — plugin already exists
Invocation: /scaffold-plugin personal-plugin
Must:
- Detects that
plugins/personal-plugin/already exists - Prompts to confirm overwrite or aborts
- Does not overwrite existing plugin silently
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.
- 9d ago First seen · 101 lines · 0 tokens per session scan C adfc7bb80768
scaffold-plugin.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 590 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.