compliance-analysis

compliance-analysis is a skill for Claude Code, Codex from Global-Slice/claude-plugin. It costs 98 tokens per session (1,347 once invoked), scanned A, original, MIT.

A guide for reviewing a company's compliance tickets and overall compliance status using Slice data. It helps interpret issues involving stakeholders, securities, equity plans, valuations, taxes, and cap tables.

In plain words
What is it for?
Use it to review open, completed, or urgent compliance issues, group them by severity or affected object, and inspect the full tickets for a specific company record.
Why use it?
It organizes compliance findings and separates recorded ticket details from broader domain interpretation. It also prevents using general legal advice as a replacement for the company's actual ticket data.

Skill for Claude CodeCodex

Part of the slice-global plugin — 8 skills, 1 MCP server shipped together

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 skills/global-slice/claude-plugin/compliance-analysis
Any agent
npx skills add Global-Slice/claude-plugin --skill compliance-analysis
Clone the repo
git clone --depth 1 https://github.com/Global-Slice/claude-plugin

Made for: Claude Code, Codex.

Or install slice-global, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

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 compliance-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/global-slice/claude-plugin/compliance-analysis.svg)](https://agentmods.dev/skills/global-slice/claude-plugin/compliance-analysis)
Your own site
<a href="https://agentmods.dev/skills/global-slice/claude-plugin/compliance-analysis"><img src="https://agentmods.dev/badge/skills/global-slice/claude-plugin/compliance-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,347 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00098 $0.01347
Opus 5 $0.00049 $0.00674
Sonnet 5 $0.00020 $0.00269
Haiku 4.5 $0.00010 $0.00135

Measured 4d ago against content hash 19aeb146545c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compliance-analysis 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 4d 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.

plugins/slice-global/skills/compliance-analysis/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance Analysis

Scope

Use for compliance tickets and posture. Not a substitute for legal advice. For workflow process status without compliance focus, use workflows-analysis. For cap-table totals without compliance tickets, use cap-table-analysis.

Core Principle

Use compliance tools as a compliance-ticket interface, not as a raw data export. Start with the bounded aggregate breakdown, then retrieve full ticket records only for a specific object after identifying that object with the relevant domain tool.

Slice data and compliance tickets are the ground truth for a specific company. Do not replace ticket findings with general legal advice. Use domain knowledge to interpret why a ticket matters, and separate "the ticket says" from "the domain implication is".

Tool Selection

  1. Use compliance_get_tickets_breakdown first for company-level compliance posture. It returns fixed-size aggregates only: total, active, completed, archived, status counts, severity counts, object type counts, top issue groups capped to 10, and time-sensitive counts.
  2. Use compliance_get_object_tickets only for one known object. It returns full ticket records for objectId and objectType, including status, comments, events, ticketData, due date, and metadata.
  3. Use domain tools to resolve the object before calling object tickets: stakeholder tools for stakeholders, securities tools for grants and shares, equity-pool tools for equity pools, valuation tools for FMV records, cap-table tools for cap-table context, and exercise-request tools when available.

Do not call object-ticket retrieval broadly across many objects unless the user explicitly asks for detailed ticket bodies and the object set is small.

Object Types

compliance_get_object_tickets requires an object ID and one of these ticket object types:

  • corporateApprovals
  • exerciseRequests
  • grants
  • stakeholders
  • valuations
  • equityPools
  • equityPlans
  • shares

Use the object type that matches the compliance object, not the endpoint family used to discover it. For example, a grant discovered through securities_search still uses objectType: "grants".

Read the full file on GitHub · 92 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. 4d ago First seen · 92 lines · 98 tokens per session scan A 19aeb146545c

Subscribe to this mod's changes

compliance-analysis is a skill published in the GitHub repository Global-Slice/claude-plugin (9 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,347 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 2026-08-31.

Related

Other skills, from other repositories