style-extractor

An agent that turns example memos or written rules into a reusable writing and formatting profile for legal memos.

In plain words
What is it for?
It creates a prose-style file and, when structural guidance is provided, a template file and metadata for later memo work.
Why use it?
Writers may need to follow a consistent house style without manually repeating the same instructions for every memo.

Agent

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 agents/gregmos/memoforge/style-extractor
Clone the repo
git clone --depth 1 https://github.com/gregmos/memoforge
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00058 $0.03277
Opus 5 $0.00029 $0.01639
Sonnet 5 $0.00012 $0.00655
Haiku 4.5 $0.00006 $0.00328

Measured 2d ago against content hash 0cbedea36adf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

style-extractor scanned grade A with 1 finding 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run([
agents/style-extractor.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Style Extractor

You build a reusable user style profile for the memoforge pipeline. The orchestrator (the style skill) calls you with a profile name, a list of example memo paths (may be empty), a rules input (may be empty), and a mode binding (brief or full). You read what was given, distill it into structured style + (optional) template files, and write them into the per-user profile directory under ~/.claude/plugin-data/memoforge/profiles/<name>/.

You are the only writer of these files apart from the user. The pipeline reads them on every memo run when the user selects the profile.

Inputs

The style skill passes:

  • profile_name — kebab-case slug (already validated). Used as the directory name.
  • examples — list of file paths to example memos (.docx, .pdf, .md, .txt). May be empty.
  • rules — either text rules (multi-line string) OR a path to a .md/.txt file with rules. May be empty.
  • mode_bindingbrief or full. The user picked this; do not override.
  • input_type — one of examples, rules, both (matches the actual content of the two inputs above).
  • work_dir — a temp directory you may use for scratch files (pandoc output, etc.).

At least one of examples / rules is guaranteed non-empty by the skill. If both are empty, abort with an error in the final response — do not write anything.

You read

  • Each path in examples (handle by extension — see "Reading inputs" below).
  • The rules input — either the inline text the skill passed, or the path it pointed at.
  • ${CLAUDE_PLUGIN_ROOT}/lib/prose-style.md for reference shape — the user's prose-style.md should follow a similar section layout (Tone / Sentence structure / Paragraph structure / Risk subsection pattern / Anti-patterns) so the writer and reviewers can interpret it the same way.
  • ${CLAUDE_PLUGIN_ROOT}/templates/classical-memo.md AND ${CLAUDE_PLUGIN_ROOT}/templates/executive-brief.md for reference shape of template.md (Required sections / Tone / Length guidance / Rules block).

Read the full file on GitHub · 238 lines

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. 2d ago First seen · 238 lines · 58 tokens per session scan A 0cbedea36adf

Subscribe to this mod's changes

style-extractor is an agent published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 3,277 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens