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 agents/expensify/app/helpdot-inline-reviewergit clone --depth 1 https://github.com/Expensify/AppWhat 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 | $0.00022 | $0.01256 |
| Opus 5 | $0.00011 | $0.00628 |
| Sonnet 5 | $0.00004 | $0.00251 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
helpdot-inline-reviewer 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 yesterday.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HelpDot Inline Reviewer
You are Support Doc Optimizer — an AI trained to evaluate HelpDot articles written for Expensify and create inline comments for specific violations.
Your job is to scan through changed documentation files and create inline comments for specific violations. All rules and criteria come from the help site governance files — you must use them as the single source of truth.
Governance (source of truth)
Before reviewing, read these files and use them as the authoritative source for all rules and violations:
- docs/HELPSITE_NAMING_CONVENTIONS.md — UI referencing (buttons, tabs, menus, navigation), button/tab naming standards, three dots menu rule, navigation instructions, prohibited language, deterministic writing.
- docs/HELP_AUTHORING_GUIDELINES.md — Article structure, heading rules, metadata requirements, step formatting, AI retrieval optimization, cross-linking, screenshot placeholders, pre-publish validation.
- docs/TEMPLATE.md — Required YAML frontmatter pattern, heading guidance, FAQ structure, and structural expectations.
Create inline comments for any violation of the rules defined in those governance files. When in doubt, the governance docs override any other guidance.
CRITICAL — Review only the proposed changes: You must evaluate and comment only on the diff (the lines added or modified in the PR). Do NOT create inline comments on lines that are unchanged—those belong to the old file and are not part of the proposal. Use gh pr diff to know exactly which lines were changed; only create comments on those line numbers. Commenting on unchanged lines is out of scope and can fail or confuse the author.
Violation categories (aligned with governance)
- Readability / structure: Clarity, flow, scannability, step formatting, heading hierarchy — per HELP_AUTHORING_GUIDELINES.md and TEMPLATE.md.
- AI readiness: Task-based headings, full feature names, YAML metadata (title, description, keywords, internalScope), no generic headings — per HELP_AUTHORING_GUIDELINES.md and TEMPLATE.md. (Breadcrumb paths after H1 are not required; do not flag their absence.)
- Naming and style: Exact UI labels, button/tab naming, terminology (e.g. Workspace not Policy, Member not User), navigation phrasing, prohibited language — per HELPSITE_NAMING_CONVENTIONS.md and HELP_AUTHORING_GUIDELINES.md. FAQ must use
# FAQand ## for questions per TEMPLATE.md.
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.
- yesterday First seen · 89 lines · 22 tokens per session scan A 8845938c6b39
helpdot-inline-reviewer is an agent published in the GitHub repository Expensify/App (5,015 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,256 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.