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.
npx skills add darthzen/fossa-mcp --skill fossa-vuln-exportgit clone --depth 1 https://github.com/darthzen/fossa-mcpWrote 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/skills/darthzen/fossa-mcp/fossa-vuln-export)<a href="https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-vuln-export"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-vuln-export/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/skills/darthzen/fossa-mcp/fossa-vuln-export"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-vuln-export.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 | $0.00099 | $0.05383 |
| Opus 5 | $0.00049 | $0.02691 |
| Sonnet 5 | $0.00020 | $0.01077 |
| Haiku 4.5 | $0.00010 | $0.00538 |
Grade A, and why
fossa-vuln-export 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 9d 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fossa-vuln-export
Read a project's vulnerability findings out of FOSSA, join each one to the dependency it lives in, and emit a document in a standard format — OSV by default, CycloneDX 1.6 VDR on request — so the findings can be compared mechanically against another scanner's output. Given another vendor's export, normalize both sides to the same keys and report where they agree, where they differ, and where they disagree about severity.
Why this workflow exists: every scanner invents its own JSON, so "how does FOSSA compare to Snyk" usually degenerates into two people reading two files and arguing about counts. Normalizing both sides to (package identity, vulnerability identity) keys turns that argument into a join. The join is only honest if the normalization is: aliases resolved, versions treated consistently, scope differences named. This skill does the normalization and names the residual judgment calls instead of burying them.
The honest framing, stated up front and never dropped: a diff of two scanner outputs measures detection differences, not correctness. A "FOSSA-only" finding is not automatically a win and a "vendor-only" finding is not automatically a miss — either can be a true positive the other scanner scoped out, a version-range disagreement, or an alias the normalization failed to resolve. Spot-check before you characterize, and present counts with their caveats attached.
This skill exports and compares facts. When the user wants the findings ranked — which project or package to fix first — that is [[fossa-suggest-score]], which layers reachability and exposure judgment on top of the same data. Do not blend the two: an export contains only what FOSSA returned.
Ask which project (and, for mode 2, for the vendor file) if it isn't obvious. Everything else is procedure.
1. Resolve the project
fossa_list_projects(title=...)
Never guess a locator from a repo name. The listing gives you the exact
locator (e.g. git+github.com/acme/widget) and latestRevision.locator
(e.g. git+github.com/acme/widget$abc123), and you need both downstream. If
the user wants a specific revision rather than the latest, resolve it with
fossa_list_project_revisions(project_locator=...).
What ships with it
1 file 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.
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.
- 9d ago First seen · 367 lines · 99 tokens per session scan A 4fc607357a56
fossa-vuln-export is a skill published in the GitHub repository darthzen/fossa-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 5,383 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…