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 agentmods add instructions/crowdsecurity/crowdsec-skill/claude-mdgit clone --depth 1 https://github.com/crowdsecurity/crowdsec-skillWhat 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 | $0.02212 | $0.02212 |
| Opus 5 | $0.01106 | $0.01106 |
| Sonnet 5 | $0.00442 | $0.00442 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade B, and why
crowdsec-skill CLAUDE.md scanned grade B with 2 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
invocation differs (`sudo cscli …` → `docker exec <name> …` → `kubectl exec -n <ns> <pod> -- …`). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
HTTPS, not systemd/docker/k8s — so no per-platform prefixes), and recipes are `curl` the skill runs How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Conventions for authoring this skill. This governs how skill content is written and validated.
General rules
Never open responses with filler phrases like "Great question!", "Of course!", "Certainly!", or similar warmups. Start every response with the actual answer. No preamble, no acknowledgment of the question.
Match response length to task complexity. Simple questions get direct, short answers. Complex tasks get full, detailed responses. Never pad responses with restatements of the question or closing sentences that repeat what you just said.
Before any significant task, show me 2-3 ways you could approach this work. Wait for me to choose before proceeding.
If you are uncertain about any fact, statistic, date, or piece of technical information: say so explicitly before including it. Never fill gaps in your knowledge with plausible-sounding information. When in doubt, say so.
Writing style
- Be concise. Technical documentation, not an essay. Favor tables, command recipes, and short imperative sentences. Cut throat-clearing, restated context, and filler.
- Write only the final, correct information. Never record self-corrections, dead ends, or
"actually, it turned out…" narration discovered while authoring. The reader gets the conclusion,
not the journey. This applies equally to inline expected-output hints: state the correct
outcome, never the wrong-then-fixed version. Do not annotate verification inline in prose (no
"(verified)", "Verified on…", "verified gotcha"). Record verification in the per-file
verified:frontmatter block instead — see Verification tracking below. - Keep
SKILL.mda router. It is an index and decision layer that points toreferences/. Depth and recipes belong in the reference docs, not inSKILL.md. - Cover every environment. Each command or recipe carries its systemd / docker / k8s variant, matching the existing convention. If some command or recipe is irrelevant to some variant it should be noted.
- Anchor to canonical docs. Each reference doc cites the upstream CrowdSec docs URL it derives from. Claims trace to canonical documentation, not to memory.
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.
- 3d ago First seen · 142 lines · 2,212 tokens per session scan B ca993336782b
crowdsec-skill CLAUDE.md is an instructions file published in the GitHub repository crowdsecurity/crowdsec-skill (23 stars, last pushed 15d ago), licensed MIT. It adds 2,212 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.