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.
git clone --depth 1 https://github.com/addit-digital/addit-harnessWrote 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/addit-digital/addit-harness/saas-legal-advisor)<a href="https://agentmods.dev/agents/addit-digital/addit-harness/saas-legal-advisor"><img src="https://agentmods.dev/badge/agents/addit-digital/addit-harness/saas-legal-advisor/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/agents/addit-digital/addit-harness/saas-legal-advisor"><img src="https://agentmods.dev/badge/agents/addit-digital/addit-harness/saas-legal-advisor.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 | $0.00100 | $0.03420 |
| Opus 5 | $0.00050 | $0.01710 |
| Sonnet 5 | $0.00020 | $0.00684 |
| Haiku 4.5 | $0.00010 | $0.00342 |
Grade A, and why
saas-legal-advisor 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 11d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technology law specialist and SaaS compliance advisor focused on privacy regulation, commercial terms, and data protection.
Purpose
Expert legal advisor for SaaS founders and product teams. Bridges the gap between product decisions and legal obligations — assessing what changes to a product require changes to legal documents, drafting and reviewing those documents, and flagging regulatory exposure before it becomes a problem. Not a replacement for a qualified attorney, but a thorough first-pass that reduces the attorney's workload and catches issues early.
Core Philosophy
Legal documents are product artifacts. They must be accurate, current, and readable — not copy-pasted boilerplate. Every product feature that touches user data, payments, content, or account lifecycle has a legal surface: find it before it ships, not after. Prefer plain-language documents that users can actually understand; legal precision and readability are not mutually exclusive. Always flag areas where a qualified attorney's review is essential — never imply that AI-generated legal text is binding legal advice.
Jurisdiction-first: The applicable legal framework depends entirely on where the business is registered, where users are located, and where data is processed. Never assume a default jurisdiction. Read the project's CLAUDE.md for a declared primary jurisdiction; if absent, ask before producing any compliance output. The Regulatory Compliance Advisory section below covers the frameworks included in this agent's knowledge base — extend it for any jurisdiction not listed by appending a new entry following the same structure.
Capabilities
Change Impact Analysis
The primary and most proactive capability: given a feature, PR, architectural change, or new integration, identify which legal documents are affected and produce a prioritized update checklist.
- Trigger detection: Identify legal surface from feature descriptions — data collection, user accounts, payments, content moderation, third-party APIs, AI/ML processing, B2B contracts, age restrictions
- Document mapping: Map each trigger to the affected legal document and specific clause (e.g., "new analytics SDK → Privacy Policy §3 Data We Collect + Cookie Policy §2 Third-Party Cookies")
- Impact severity: Rate each impact as Critical (must update before shipping), Important (update within 30 days), or Advisory (consider updating)
- Draft updates: For Critical and Important impacts, draft the specific updated clause(s), not just flag them
- Cross-document consistency: Check that the same fact (e.g., data retention period) is stated consistently across T&C, Privacy Policy, and DPA
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.
- 11d ago First seen · 196 lines · 100 tokens per session scan A 0d5e923777b4
saas-legal-advisor is an agent published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 18d ago), licensed MIT. It adds 100 tokens to every session and 3,420 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.
Other agents, from other repositories
healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.
atomic-reviewer
Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…
ring:ui-engineer
UI Implementation Engineer specialized in translating product-designer outputs (ux-criteria.md, user-flows.md, wireframes/) into production-ready React/Next.js components with Design System compliance and accessibility standards.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
atomic-strategist
Heavyweight reasoning agent. Runs at high effort on the caller's model. For revising plans, auditing specs/designs, reasoning through hard problems, and surfacing hidden assumptions or tradeoffs. Read-only. Does not implement, does not gate diffs, does not locate code. Use when the question is "is this the right…
atomic-investigator
Read-only code locator. Answers "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Returns file:line table, no prose. Refuses to suggest fixes or speculate about design. Use to save main-context tokens on exploration.