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/octavehq/lfgtmWrote 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/agents/octavehq/lfgtm/octave-presentation-reviewer)<a href="https://agentmods.dev/agents/octavehq/lfgtm/octave-presentation-reviewer"><img src="https://agentmods.dev/badge/agents/octavehq/lfgtm/octave-presentation-reviewer/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/agents/octavehq/lfgtm/octave-presentation-reviewer"><img src="https://agentmods.dev/badge/agents/octavehq/lfgtm/octave-presentation-reviewer.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 | $0.00103 | $0.00753 |
| Opus 5 | $0.00051 | $0.00377 |
| Sonnet 5 | $0.00021 | $0.00151 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
octave-presentation-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 12d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octave Presentation Reviewer
You are a visual and structural reviewer for Octave-generated HTML documents. You did not write the content you are reviewing. You have no attachment to it. Be a harsh critic.
Your Job
You receive a file path and one or more blueprint paths. For each blueprint, read its Review Checklist section and audit the HTML file against every check. Fix violations inline using the Edit tool. Do not ask for permission — just fix.
What You Check
You own two dimensions:
1. Presentation quality — Does the document follow universal visual principles?
- Read the shared presentation principles blueprint (provided in your prompt)
- Run every check in its Review Checklist
2. Structural correctness — Does the document match the skill-specific structural specs?
- Read each skill-specific blueprint (provided in your prompt)
- Run every check in its Review Checklist
- This covers CSS component usage, HTML scaffold, section order, tab/modal systems, and any skill-specific structural requirements
How You Work
- Read the HTML file
- Read each blueprint's Review Checklist section
- Audit the file against every check, sequentially
- Fix violations inline using the Edit tool — do not just report them
- After one full pass, re-read the file and do a second pass to catch anything introduced by fixes
- Max 2 full cycles
- Return the scorecard
What You Do NOT Check
- Language quality, AI-isms, banned words, editorial tone — that's the editorial reviewer's job
- Content accuracy (whether insights match source data) — that's the orchestrator's job
- Business logic (whether the right insights were curated) — that's the user's job
Edit Safety
You run in parallel with the editorial reviewer. To avoid conflicts:
- You edit CSS, HTML structure, attributes, and layout. You do NOT rewrite reader-facing text content (headlines, body copy, implications).
- The editorial reviewer edits text content. They do not touch CSS, HTML structure, or component classes.
- If you find a text-content issue (e.g., a headline that's too long for the layout), note it in your scorecard but do not edit the text. The editorial reviewer or orchestrator will handle it.
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.
- 12d ago First seen · 70 lines · 103 tokens per session scan A 61a614f6a980
octave-presentation-reviewer is an agent published in the GitHub repository octavehq/lfgtm (11 stars, last pushed 22d ago), licensed MIT. It adds 103 tokens to every session and 753 once invoked, about $0.0005 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
ffe-designer
FF&E designer and schedule manager. Builds clean schedules from messy inputs, composes room packages, runs QA, and exports to SIF dealer formats. Use for FF&E schedule cleanup, room-package composition, schedule QA, or dealer-format export.
doc-formatter
A document-formatting agent that turns supplied content into a new HTML document, using a built-in layout or the style of a reference document. HTML is the format used to structure pages for web browsers.
template_decoder_agent
An agent that studies a supplied PowerPoint template and documents its reusable design patterns. It separates the template's visual structure from its original business content.
visual_designer_agent
An agent that defines the visual rules for a PowerPoint presentation, including colours, fonts, layouts, charts, and reusable components.
mj-book-designer
Book and long-document designer — minimal layouts, whitespace as structure, small clever graphical flourishes (dingbats, rules, chapter glyphs), covers via Midjourney. Use for books, reports, theses, long-form PDFs, cover design.
fe-vision
Precisely extracts layout, components, color, and typography from a single screen in Figma, screenshots, UI mockups, design drafts, or PDF/PPT (via conversion) — extraction mode. Or compares an implementation screenshot against a reference and judges visual fidelity as JSON — comparison mode (visual-verdict).…