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 skills add bdongucla/math-ai-review-skills --skill report-reviewgit clone --depth 1 https://github.com/bdongucla/math-ai-review-skillsWrote 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/skills/bdongucla/math-ai-review-skills/report-review)<a href="https://agentmods.dev/skills/bdongucla/math-ai-review-skills/report-review"><img src="https://agentmods.dev/badge/skills/bdongucla/math-ai-review-skills/report-review/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/skills/bdongucla/math-ai-review-skills/report-review"><img src="https://agentmods.dev/badge/skills/bdongucla/math-ai-review-skills/report-review.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 | $0.00089 | $0.05876 |
| Opus 5 | $0.00044 | $0.02938 |
| Sonnet 5 | $0.00018 | $0.01175 |
| Haiku 4.5 | $0.00009 | $0.00588 |
Grade A, and why
report-review 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
About This Skill This skill distills review practice on policy and technical analysis reports in mathematics, AI, and adjacent fields, and applies broadly to non-academic document review.
Report Review Skill
A rigorous review framework for non-academic documents: policy analysis reports, technology and market assessments, internal decision memos, project materials, and similar.
Distinction from paper-review: paper-review targets academic manuscripts (contribution attribution, incremental quantification, full reading of prior work); this skill targets decision-maker-facing documents (factual accuracy, tight reasoning, actionable recommendations). Both share the evidence-based review discipline, but differ in process and emphasis.
Trigger scenarios: policy recommendations, technology assessment reports, market analyses, internal decision documents, project proposal drafts, white paper drafts.
Trigger phrases: review report, policy review, white paper review, revision feedback, document assessment
Core Principles
-
Identify problems only - no praise. Every line of the review output is devoted to surfacing issues and offering actionable revision suggestions. The overall assessment summarizes what the document does and what problem categories were found; it contains no positive evaluation. Rationale: the reader needs improvement directions, not encouragement.
-
Evidence-based review discipline (inherited from paper-review): Every critique must have a clear claim, supporting evidence, and self-consistent reasoning. Judgments without evidence are labeled "personal inference"; such items must not exceed 20% of all critique items. This is an internal thinking discipline - in the output, evidence and reasoning flow naturally into the prose rather than appearing as a rigid three-part format.
-
Evidence-Based: Spot-check factual claims (data, dates, attributions, comparisons) in the report rather than exhaustively verifying every claim. See the sampling rules in Step 2.
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 · 347 lines · 89 tokens per session scan A c45161a8856c
report-review is a skill published in the GitHub repository bdongucla/math-ai-review-skills (11 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 5,876 once invoked, about $0.0004 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 skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.