review-helpdot-pr

A review command for HelpDot documentation pull requests, which are proposed sets of changes to project documentation. It uses the project’s naming, authoring, template, and validation rules to run an inline review and a summary review.

In plain words
What is it for?
Use it to review HelpDot documentation changes, add line-specific feedback, and post a top-level summary with scores and recommendations.
Why use it?
Documentation pull requests can contain small naming, structure, metadata, or navigation mistakes. This checks changed files and reports specific problems as well as an overall assessment.

Command for Claude Code

▶ How to Add Interactive UIs in Claude and ChatGPT via MCP Apps GritAI Studio · about Expensify/App · on YouTube →
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.

agentmods
npx agentmods add commands/expensify/app/review-helpdot-pr
Clone the repo
git clone --depth 1 https://github.com/Expensify/App

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 271 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00007 $0.00271
Opus 5 $0.00003 $0.00135
Sonnet 5 $0.00001 $0.00054
Haiku 4.5 $0.00001 $0.00027

Measured 3d ago against content hash 92eb9c1f77da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-helpdot-pr 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 3d 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-helpdot-pr.md · 29 lines

What it actually says

Perform a comprehensive HelpDot documentation review using two specialized subagents. Both reviewers use the help site governance files in the repo as the source of truth for rules and scoring:

  • docs/HELPSITE_NAMING_CONVENTIONS.md — UI referencing, button/tab naming, navigation
  • docs/HELP_AUTHORING_GUIDELINES.md — Structure, headings, metadata, AI retrieval, validation
  • docs/TEMPLATE.md — YAML frontmatter, heading guidance, FAQ structure

Step 1: Inline Review

Use the helpdot-inline-reviewer agent to:

  • Scan all changed documentation files
  • Create inline comments for violations of the governance rules above
  • Focus on line-specific, actionable feedback

Step 2: Summary Review

Use the helpdot-summary-reviewer agent to:

  • Analyze the overall quality of all changes using the governance criteria
  • Provide comprehensive assessment with scoring
  • Post one top-level PR comment with summary and recommendations

Run both agents and ensure their feedback is posted to the PR.

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. 3d ago First seen · 29 lines · 7 tokens per session scan A 92eb9c1f77da

Subscribe to this mod's changes

review-helpdot-pr is a command published in the GitHub repository Expensify/App (5,017 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 271 once invoked, about $0.0000 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 2026-08-30.