What is finish-document?

A command that finds questions, TBDs, and unfinished points in a document, asks for answers, and updates the document with the resolved information. It can also choose recommended answers automatically.

Use it to complete product requirements documents, specifications, and other files containing unanswered questions or placeholder decisions.

It helps finish incomplete requirements or planning documents without searching through them manually for every open item.

finish-document — Command for Claude Code by davistroy

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/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/finish-document/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/finish-document)

Your own site

<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/finish-document"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/finish-document/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/finish-document"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/finish-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,561 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.03561
Opus 5	$0.00008	$0.01781
Sonnet 5	$0.00003	$0.00712
Haiku 4.5	$0.00002	$0.00356

Measured 10d ago against content hash be5460583434, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

finish-document 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 10d 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.

plugins/personal-plugin/commands/finish-document.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finish Document

Complete an incomplete document by extracting all questions/TBDs, walking through them interactively, and updating the document with the resolved answers.

Input Validation

Required Arguments:

<document-path> - Path to the document to complete

Optional Arguments:

--auto - Auto-select recommended answers instead of interactive Q&A (user can still override)
--force - Proceed even if schema validation fails for intermediate files (not recommended)

Validation: If the document path is missing, display:

Usage: /finish-document <document-path> [--auto] [--force]
Example: /finish-document PRD.md
Example: /finish-document docs/requirements.md --auto

Input

The user will provide a document path after the command (e.g., /finish-document PRD.md).

Optional flags:

--auto — Auto-select recommended answers instead of interactive Q&A (user can still override)

Workflow Overview

┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│  1. Extract     │────▶│  2. Answer      │────▶│  3. Update      │
│     Questions   │     │     Questions   │     │     Document    │
└─────────────────┘     └─────────────────┘     └─────────────────┘
        │                       │                       │
        ▼                       ▼                       ▼
   questions.json          answers.json          backup + updated
   (in reference/)         (in reference/)       original document

Instructions

This command executes three phases sequentially: extract questions, answer them interactively, and update the document with resolved answers.

Phase 1: Setup and Question Extraction

1.1 Validate Input

Confirm the specified document exists
Read and parse the document
Create reference/ folder if it doesn't exist

1.2 Extract Questions

Execute the logic from /define-questions:

Identify all questions and open items:
- Explicit questions (sentences ending with ?)
- Open items marked with "TBD", "TODO", "TBC", or similar markers
- Incomplete sections or placeholders
- Areas marked as needing review or decision
- Gaps in specifications or requirements
- Ambiguous or vague statements that need clarification
- Missing details needed for implementation
- Dependencies or prerequisites that are undefined
- Edge cases or scenarios not addressed

Read the full file on GitHub · 394 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.

10d ago First seen · 394 lines · 15 tokens per session scan A be5460583434

Subscribe to this mod's changes

finish-document is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 3,561 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.

Documents

brand-generate

Generate an on-brand document from a saved Brand Profile.

ferdinandobons/brand-docs · 0 tokens

cti-report

Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].

7onez/cti-expert · 45 tokens

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…

ihudak/ihudak-claude-plugins · 67 tokens

finish-document