ClassifyCCP

ClassifyCCP is a skill for Claude Code, Codex from LegalQuants/lq-skills. It costs 76 tokens per session (2,712 once invoked), scanned A, original, Apache-2.0.

A document-review workflow for finding and classifying references to Competition Compliance Programmes, or company systems for following competition law, in enforcement documents. It converts PDFs to text, translates non-English documents, analyses them, and records results in an Excel file.

In plain words
What is it for?
It is for reviewing competition-law enforcement policies, cases, and judgments, especially when the source is a PDF or is not written in English.
Why use it?
It provides a consistent way to review long policy documents and legal cases without missing relevant passages. The classification explains whether a compliance programme is treated as an offence, defence, remedy, or irrelevant.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing competition-law enforcement policies, cases, and judgments, especially when the source is a PDF or is not written in English.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/legalquants/lq-skills/classify-ccp
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.

Any agent
npx skills add LegalQuants/lq-skills --skill classify-ccp
Clone the repo
git clone --depth 1 https://github.com/LegalQuants/lq-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ClassifyCCP

README.md
[![agentmods](https://agentmods.dev/badge/skills/legalquants/lq-skills/classify-ccp/github.svg)](https://agentmods.dev/skills/legalquants/lq-skills/classify-ccp)
Your own site
<a href="https://agentmods.dev/skills/legalquants/lq-skills/classify-ccp"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/classify-ccp/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.

agentmods 80×15 button for ClassifyCCP

Your own site · 80×15
<a href="https://agentmods.dev/skills/legalquants/lq-skills/classify-ccp"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/classify-ccp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00076 $0.02712
Opus 5 $0.00038 $0.01356
Sonnet 5 $0.00015 $0.00542
Haiku 4.5 $0.00008 $0.00271

Measured 12d ago against content hash 7472c13cafd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ClassifyCCP 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.

skills/classify-ccp/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCP Classification

Structured workflow for classifying how Competition Compliance Programmes (CCPs) are treated in competition enforcement documents (policy documents and cases/judgments).

Workflow Overview

  1. Convert — PDF → Markdown using PyMuPDF
  2. Translate — If not English, translate to English
  3. Analyse — Read entire document, identify all CCP-relevant paragraphs
  4. Classify — Assign category based on full understanding
  5. Scratchpad — Save working notes and classification to file
  6. Excel — Ask permission, then populate Output.xlsx

Phase 1: Convert PDF to Markdown

When the user provides a PDF file path:

  1. Run the following Python snippet via Bash to extract text:

    import fitz, sys
    doc = fitz.open(sys.argv[1])
    md = "\n\n".join(page.get_text("text") for page in doc)
    with open("_tmp_converted.md", "w", encoding="utf-8") as f:
        f.write(md)
    print("Converted successfully.")
    

    Example: python3 -c "..." path/to/document.pdf

  2. Read _tmp_converted.md to confirm content loaded correctly.

  3. Inform user: "PDF converted. Beginning analysis..."


Phase 2: Language Check & Translation

  1. Read _tmp_converted.md.
  2. Determine the language of the document.
  3. If NOT English: translate the entire content into fluent English, preserving all structure and formatting. Overwrite _tmp_converted.md with the translated content.
  4. If English: proceed directly.

Phase 3: Full Document Analysis

Read the entire converted markdown. Do not skim — classification must be based on a full understanding of the document.

3a. Extract document metadata (needed for Excel if a new row must be created):

  • Name of Document (Col A): PDF basename without extension (e.g., Case_EU_1)
  • Country / Authority (Col B): the jurisdiction or authority the document relates to (e.g., EU, UK, France, Canada Competition Bureau)
  • Document Type (Col C): one of Policy Document, Case, Judgment, Decision, Guidelines, or similar
  • Title (Col D): the official title of the document as found in its header/cover
  • Date (Col E): the date of publication, decision, or last modification as stated in the document; if not found, use the PDF file's modification date

Read the full file on GitHub · 203 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 203 lines · 76 tokens per session scan A 7472c13cafd9

Subscribe to this mod's changes

ClassifyCCP is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 2,712 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.