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 magnus919/agent-skills --skill crowdsecgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/crowdsec)<a href="https://agentmods.dev/skills/magnus919/agent-skills/crowdsec"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/crowdsec/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/magnus919/agent-skills/crowdsec"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/crowdsec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.01615 |
| Opus 5 | $0.00041 | $0.00807 |
| Sonnet 5 | $0.00016 | $0.00323 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
crowdsec 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 6d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrowdSec
CrowdSec detects hostile behavior from logs and HTTP requests, then exposes alerts and decisions through LAPI. The engine alone does not block traffic: install and verify at least one remediation component (bouncer) before claiming protection.
Safety Gate
Before any mutation, confirm the target host/container, scope, backup or rollback,
and maintenance window. Prefer read-only inspection and simulation first. Never
manually delete decisions, collections, or data without recording the reason and
an undo path. Save bouncer keys when created; they are shown once. Use
simulation: true while tuning scenarios so detections are observed without
enforcement, then verify allowlists before live blocking.
Choose a Deployment
For Debian/Ubuntu, add the CrowdSec repository, install crowdsec, then install
a remediation package such as crowdsec-firewall-bouncer-iptables or
-nftables. For Docker Compose, expose LAPI (127.0.0.1:8080), metrics
(127.0.0.1:6060), and AppSec (127.0.0.1:7422) only to required networks,
mount /etc/crowdsec, /var/lib/crowdsec/data, and logs read-only, and pin a
reviewed image version. Persist the data directory, mandatory for v1.7.0+.
Load the Docker deployment guide for a full
compose example and remote-agent caveats.
After installation, verify systemctl status crowdsec (or container health),
then cscli version, cscli collections list, acquisition metrics, and
bouncer connectivity. Do not expose LAPI or AppSec publicly without an explicit
network and authentication design.
The Detection-to-Blocking Workflow
- Select collections for the actual log format, for example
crowdsecurity/linux,sshd,nginx,traefik, orbase-http-scenarios. - Configure acquisition in
/etc/crowdsec/acquis.yamloracquis.d/; every source needslabels.typeso the correct parser runs. Usepoll_without_inotify: truefor unreliable NFS/SMB or bind mounts anduse_time_machine: truefor buffered logs. - Check parser/scenario hits and unparsed lines with
cscli metrics -o json. - Use profiles to map alerts to decisions. Keep
profiles.yaml.localand remember YAML sequences replace rather than merge. - Add a bouncer with
cscli bouncers add NAME, store its one-time key securely, and verifycscli bouncers listplus a harmless test decision. - Confirm the reverse proxy/firewall is actually enforcing decisions; an alert or LAPI decision alone is not proof of a blocked request.
What ships with it
13 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.
- evals/evals.json 5.6 KB
- README.md 1.5 KB
- references/appsec-deep-dive.md 3.6 KB
- references/config-reference.md 4.1 KB
- references/cscli-command-reference.md 4.6 KB
- references/database-config.md 2.9 KB
- references/docker-deployment.md 3.4 KB
- references/hub-collections.md 3.4 KB
- references/nginx-bouncer.md 2.4 KB
- references/operations-checklist.md 1.4 KB
- references/production-hardening.md 3.4 KB
- references/traefik-bouncer.md 3.7 KB
- references/troubleshooting.md 4.2 KB
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.
- 6d ago Changed · -352 lines · +12 tokens per session scan B → A 4722c930da55
- 10d ago First seen · 499 lines · 69 tokens per session scan B 9cc4b9c6952c
crowdsec is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,615 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 2026-08-30.
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…