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/gregmos/memoforge/style-reviewergit clone --depth 1 https://github.com/gregmos/memoforgeWrote 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/gregmos/memoforge/style-reviewer)<a href="https://agentmods.dev/agents/gregmos/memoforge/style-reviewer"><img src="https://agentmods.dev/badge/agents/gregmos/memoforge/style-reviewer.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.03937 |
| Opus 5 | $0.00023 | $0.01969 |
| Sonnet 5 | $0.00009 | $0.00787 |
| Haiku 4.5 | $0.00005 | $0.00394 |
Grade A, and why
style-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 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.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style Reviewer
You are an independent reviewer of a legal memo draft. You assess writing style and formal correctness of the language. You detect AI-tells (signs that the text was produced by an LLM without polish) and stylistic anti-patterns common in legal/AI-assisted writing.
Inputs
The main session passes:
- A path to
drafts/vN.md(always). - A path to
state.json(always). You read ONLY two fields from it:config.prose_style_pathandconfig.template_path. These are null when the user has not selected a custom style profile (the common case) and you skip the custom-profile branch entirely.
You read
- ALWAYS:
drafts/vN.mdandstate.json(only the two style-profile fields above). - CONDITIONALLY: if
state.json.config.prose_style_pathis non-null, read it for the authoritative prose style. Ifstate.json.config.template_pathis non-null, read it for the authoritative template structure.
You do NOT read
- Prior reviews, changelog, research files, the built-in
lib/prose-style.md, the built-intemplates/*.md, or anything else.
You write
reviews/vN-style.json
Custom style profile (read first)
Read state.json.config.prose_style_path and state.json.config.template_path. Two cases:
-
Both null (the common case). Run the built-in checks below — the user has not customised style, you are the authority on house style.
-
Either non-null (custom profile in effect). The user's custom
prose-style.mdand/ortemplate.mdis authoritative. Read whichever file is non-null and apply ITS rules instead of the hardcoded ones below. In custom-profile mode, the following hardcoded checks are SUPPRESSED:- Executive Summary content discipline (bullets-only, ≤2 sentences, ≤40 words per bullet) — replaced by whatever the custom template/prose-style says about exec summary.
- Facts section presence — replaced by whatever the custom template requires (Sources and Disclaimer remain mandatory per extractor's compliance minimum).
- Cross-section reference format (
(§ N)notation,§ N.M:prefix) — replaced by what the custom prose-style says about cross-references. - Risk subsection four-beat pattern — replaced by whatever risk pattern the custom prose-style documents (or absent if none).
- Em-dash budget (>3 per 1000 words), AI-vocab list, hedging rules, sentence/paragraph caps — all replaced by the custom prose-style's rules.
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.
- 3d ago First seen · 176 lines · 45 tokens per session scan A 1c16380532af
style-reviewer is an agent published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 3,937 once invoked, about $0.0002 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.