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/finish-document.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/finish-document.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/finish-document.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/finish-document.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/finish-document.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 | $0.00604 |
| Opus 5 | $0.00000 | $0.00302 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
finish-document.eval 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 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.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /finish-document
Purpose
Full pipeline: extracts questions from a document (like /define-questions), walks through answering them interactively (like /ask-questions), then updates the document with the answers. Good behavior: the source document is updated in place with answers incorporated, and TBD/open question markers are resolved.
Fixtures
| Fixture | Purpose |
|---|---|
docs/draft-prd.md |
Incomplete PRD with TBDs and open questions to resolve |
Test Scenarios
S1: Full pipeline — extract, answer, update
Setup: Copy fixtures/docs/draft-prd.md to a working copy (e.g., working-draft-prd.md) to avoid modifying the fixture.
Invocation: /finish-document working-draft-prd.md
Must:
- Extracts questions from the document (mentions count of questions found)
- Presents questions one at a time for interactive answering
- After all answers collected, updates the document with answers incorporated
- TBD markers in the document are replaced with the provided answers
- Updated document is still valid markdown
Should:
- Creates a backup of the original before modification (or mentions it's updating in place)
- Reports which sections were updated
Must NOT:
- Modify the document before all questions are answered
- Delete sections of the document while incorporating answers
- Leave raw Q&A output in the document body (answers should be integrated, not appended)
S2: Aborted session (user quits mid-way)
Setup: Start the Q&A, answer 2 questions, then respond "quit" or "exit".
Must:
- Stops the Q&A session cleanly
- Either saves partial progress or asks whether to save
- Does not leave the document in a partially-modified state without warning
S3: Document with no open questions
Setup: Use fixtures/docs/sample-prd.md which has no TBDs.
Invocation: /finish-document fixtures/docs/sample-prd.md
Must:
- Reports "No open questions found" or equivalent
- Does not modify the document
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 · 85 lines · 0 tokens per session scan A f3b1916bb2ad
finish-document.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 604 tokens. 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
brand-generate
Generate an on-brand document from a saved Brand Profile.
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
prose-review-docs
Reviews markdown documentation files or directories against the active prose style rules — the plugin's vendor-neutral baseline plus your organization's overlay when one is configured. Accepts a file path or directory (recursive). Runs prose-style-checker and optionally Vale. Supports --fix to auto-apply safe…
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
render-figures
Compile all .tex and .typ figure files in a directory.
harness-onboarding
Generate a human-readable onboarding document from HARNESS.md, AGENTS.md, and REFLECTIONLOG.md — a friendly guide for new team members.