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-protectgit 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-protect)<a href="https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-protect"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-protect/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-protect"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-protect.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 | $0.00151 | $0.10151 |
| Opus 5 | $0.00076 | $0.05076 |
| Sonnet 5 | $0.00030 | $0.02030 |
| Haiku 4.5 | $0.00015 | $0.01015 |
Grade A, and why
fossa-protect 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 8d 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 — 711 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fossa-protect
Read a project's vulnerabilities out of FOSSA, decide which are actually mitigable by a regex WAF, write sensors for those, and bind them to the right NeuVector groups in an alert-only mode.
Why this workflow exists: so the security team can mitigate immediately and unilaterally, without waiting on the dev team. In practice — especially with legacy code — the upgrade can take years or never happen at all: maintainers leave, nobody knows where the source lives or what server it runs on. The sensor is a real mitigation in its own right, not a placeholder for a fix that is presumed imminent. Plan for it to be the operative control indefinitely: write comments that survive team turnover, validate rather than assume, and treat the Protect-mode warning as more important the longer a binding will live, not less.
The honest framing, stated up front and never dropped: a NeuVector WAF sensor is regex matched against request context — nothing more. Only upgrading the vulnerable dependency closes the CVE, so every report this skill produces names the version bump that actually fixes the finding — as the parallel dev-side track, not as a reason to withhold or undersell the mitigation. Honesty cuts both ways: never inflate what a rule catches (step 3's classification), and never dismiss a validated sensor as "just a stopgap".
Ask which project if it isn't named. Everything else below is procedure.
Two enforcement tracks, by finding type. Sections 1–8 are the vulnerability → WAF sensor track (regex inspection of request context). A license conflict is a different problem with a different control — there is no attack request to regex, the finding is a legal blocker on shipping at all — and it routes to the licensing → quarantine track at the end of this file. Pick the track from the finding category; the two share the step-2 deployment-correlation discipline but nothing else.
1. Pull the findings
Resolve the project first — never guess a locator:
What ships with it
2 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.
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.
- 8d ago First seen · 711 lines · 151 tokens per session scan A 20af54a07c92
fossa-protect is a skill published in the GitHub repository darthzen/fossa-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 151 tokens to every session and 10,151 once invoked, about $0.0008 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.