fossa-license-review

fossa-license-review is a skill for Claude Code, Codex from darthzen/fossa-mcp. It costs 85 tokens per session (3,923 once invoked), scanned A, original, Apache-2.0.

A customer-focused FOSSA license audit that turns dependency license findings into shipping obligations. FOSSA is a software-composition analysis service; the audit considers how the customer distributes the software, such as shipping a binary or running a SaaS service.

In plain words
What is it for?
Use it to review whether dependencies create obligations, rank findings that require action, and separate genuine licensing issues from irrelevant warnings. It supports questions such as whether GPL or AGPL software can be included.
Why use it?
A license name alone does not say whether software can be shipped. The same license may create different obligations depending on distribution, linking, and the role of the dependency.

Skill for Claude CodeCodex

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

Good fit Use it to review whether dependencies create obligations, rank findings that require action, and separate genuine licensing issues from irrelevant warnings. It supports questions such as whether GPL or AGPL software can be included.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darthzen/fossa-mcp/fossa-license-review
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 darthzen/fossa-mcp --skill fossa-license-review
Clone the repo
git clone --depth 1 https://github.com/darthzen/fossa-mcp

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 fossa-license-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-license-review/github.svg)](https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-license-review)
Your own site
<a href="https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-license-review"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-license-review/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 fossa-license-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-license-review"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-license-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,923 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 $0.00085 $0.03923
Opus 5 $0.00043 $0.01962
Sonnet 5 $0.00017 $0.00785
Haiku 4.5 $0.00009 $0.00392

Measured 12d ago against content hash 472289a351c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fossa-license-review 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/fossa-license-review/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fossa-license-review

Read a project's licensing findings and full dependency list out of FOSSA, establish how the customer actually distributes their software, classify every license by the obligations it creates rather than by its name, and report which findings require action for this customer and which are noise.

Why this workflow exists: FOSSA tools return license names. "GPL-3.0" is not a verdict; it is an input to one. The same license is a shipping blocker in a publicly distributed binary and a non-event in a SaaS backend, and a linter with a copyleft license usually obligates nobody. The judgment that converts names into obligations lives here, not in the API.

The honest framing, stated up front and never dropped: the obligation classes below are settled, mainstream readings of these licenses, but the distribution model and linkage facts they key off are your assessment of the customer's situation, gathered in step 1. State that basis in the report. A finding classified against a guessed distribution model is worse than an unclassified one.

For a ranked score across a portfolio instead of a per-project obligations audit, use [[fossa-suggest-score]] — same copyleft tiers, quantitative track. This skill is the qualitative audit. Ask which project if it isn't named. Everything else below is procedure.

1. Establish the distribution model first

Everything downstream depends on this, so ask — or infer from the repo, deployment config, or what the user has already said — before pulling a single finding. Four models, in descending order of how much they obligate:

  1. Publicly distributed — binary, app store package, installer, npm/PyPI package, embedded firmware. Every distribution-triggered obligation is live.
  2. Distributed to customers — on-prem installs, appliances, SDKs shipped under contract. Same obligations as public distribution; the audience is smaller but the trigger is identical.
  3. SaaS-only — the code runs on the customer's servers and only its output reaches users. GPL, LGPL, and MPL obligations do not reach this deployment, because they trigger on distribution of the software itself. AGPL is the exception that does reach SaaS — flag it loudly. Its network-interaction clause is exactly the case the license was written for.
  4. Internal-only — tooling, services, and scripts that never leave the organization. Almost nothing fires; attribution obligations technically attach to copies but there is no external audience — no distributed artifact means no NOTICE file to ship, which is how step 4 states the same fact.

Read the full file on GitHub · 283 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. 12d ago First seen · 283 lines · 85 tokens per session scan A 472289a351c6

Subscribe to this mod's changes

fossa-license-review is a skill published in the GitHub repository darthzen/fossa-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 3,923 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 2026-08-31.

Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens