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 skills/servosity/msp-skills/crowdstrikenpx skills add Servosity/msp-skills --skill crowdstrikegit clone --depth 1 https://github.com/Servosity/msp-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/servosity/msp-skills/crowdstrike)<a href="https://agentmods.dev/skills/servosity/msp-skills/crowdstrike"><img src="https://agentmods.dev/badge/skills/servosity/msp-skills/crowdstrike.svg" alt="Measured on agentmods" 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 | $0.00102 | $0.05585 |
| Opus 5 | $0.00051 | $0.02792 |
| Sonnet 5 | $0.00020 | $0.01117 |
| Haiku 4.5 | $0.00010 | $0.00558 |
Grade A, and why
crowdstrike scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/crowdstrike/install.sh) The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- .claude-plugin/plugin.json 665 B
- AGENTS.md 2.3 KB
- CHANGELOG.md 6.8 KB
- cli/.golangci.yml 147 B
- cli/cmd/crowdstrike-cli/main.go 356 B
- cli/cmd/crowdstrike-mcp/main.go 2.1 KB
- cli/go.mod 969 B
- cli/go.sum 7.0 KB
- cli/internal/cache/cache.go 1.7 KB
- cli/internal/cli/agent_context.go 7.1 KB
- cli/internal/cli/alerts_get-queries-v2.go 4.3 KB
- cli/internal/cli/alerts_patch-entities-v3.go 7.3 KB
- cli/internal/cli/alerts_post-aggregates-v2.go 7.3 KB
- cli/internal/cli/alerts_post-combined-v1.go 7.0 KB
- cli/internal/cli/alerts_post-entities-v2.go 7.3 KB
- cli/internal/cli/alerts.go 830 B
- cli/internal/cli/analytics.go 5.0 KB
- cli/internal/cli/auth.go 10 KB
- cli/internal/cli/channel_workflow.go 5.3 KB
- cli/internal/cli/data_source.go 22 KB
- cli/internal/cli/deliver.go 3.5 KB
- cli/internal/cli/devices_combined-by-filter.go 16 KB
- cli/internal/cli/devices_combined-hidden-by-filter.go 16 KB
- cli/internal/cli/devices_create-host-groups.go 7.1 KB
- cli/internal/cli/devices_delete-host-groups.go 7.1 KB
- cli/internal/cli/devices_entities-perform-action.go 8.9 KB
- cli/internal/cli/devices_get-details-v2.go 3.7 KB
- cli/internal/cli/devices_get-host-groups.go 3.7 KB
- cli/internal/cli/devices_get-online-state-v1.go 3.7 KB
- cli/internal/cli/devices_perform-action-v2.go 7.9 KB
- cli/internal/cli/devices_perform-group-action.go 8.5 KB
- cli/internal/cli/devices_post-details-v2.go 7.1 KB
- cli/internal/cli/devices_query-by-filter-scroll.go 3.9 KB
- cli/internal/cli/devices_query-by-filter.go 3.8 KB
- cli/internal/cli/devices_query-combined-group-members.go 4.0 KB
- cli/internal/cli/devices_query-combined-host-groups.go 4.6 KB
- cli/internal/cli/devices_query-get-network-address-history-v1.go 7.2 KB
- cli/internal/cli/devices_query-group-members.go 4.0 KB
- cli/internal/cli/devices_query-hidden.go 3.8 KB
- cli/internal/cli/devices_query-host-groups.go 4.6 KB
- cli/internal/cli/devices_query-login-history-v2.go 7.7 KB
- cli/internal/cli/devices_update-host-groups.go 7.1 KB
- cli/internal/cli/devices_update-tags.go 7.1 KB
- cli/internal/cli/devices.go 1.7 KB
- cli/internal/cli/doctor_verdict.go 12 KB
- cli/internal/cli/doctor.go 21 KB
- cli/internal/cli/feedback.go 6.6 KB
- cli/internal/cli/fleet_alerts_test.go 1.1 KB
- cli/internal/cli/fleet_alerts.go 1.6 KB
- cli/internal/cli/fleet_policy_drift_test.go 1.5 KB
- cli/internal/cli/fleet_policy_drift.go 2.1 KB
- cli/internal/cli/fleet_remediate_test.go 3.5 KB
- cli/internal/cli/fleet_remediate.go 6.0 KB
- cli/internal/cli/fleet_rollup.go 11 KB
- cli/internal/cli/fleet_scorecard_test.go 1.7 KB
- cli/internal/cli/fleet_scorecard.go 1.7 KB
- cli/internal/cli/fleet_search_test.go 1.5 KB
- cli/internal/cli/fleet_search.go 3.2 KB
- cli/internal/cli/fleet_stale_test.go 1.2 KB
- cli/internal/cli/fleet_stale.go 1.5 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.
- today Changed · +1 lines 857d6c1b8670
- 4d ago First seen · 396 lines · 102 tokens per session scan A 59bac1cc8274
crowdstrike is a skill published in the GitHub repository Servosity/msp-skills (35 stars, last pushed 2d ago), with no licence file. It adds 102 tokens to every session and 5,585 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ha-backup-platform-add
Augments an existing Home Assistant Custom Integration with one backup-platform surface — pre/post backup hooks or a backup agent — conforming to spec/ha/backup-platform. For hooks it generates backup.py with asyncprebackup/asyncpostbackup that symmetrically pause and resume stateful operations around a backup; for an…
withings
Unofficial Withings data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Withings data or actions through an agent.
vercel-cli
Safety-first Vercel CLI (vercel/vc) skill to fully manage projects from the terminal — deploys, env vars, domains, DNS, certs, projects, teams, logs, rollbacks, promotions, firewall, and vercel api. Classifies each command by risk tier and gates destructive/forbidden ops behind confirmation. Self-heals via embedded…
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
qodo-pr-resolver
Compatibility alias for explicit qodo-pr-resolver requests. Follow the complete Qodo PR review workflow embedded here and use qodo-review-resolver for new invocations; lifecycle update provenance intentionally uses the canonical qodo-review-resolver release-index identity.
jtagprobe
Probe IoT/embedded targets for exposed SWD/JTAG debug interfaces using a SEGGER J-Link. Detects whether debug is OPEN, LOCKED (readout-protected), or DEAD (fused off). Use when assessing whether a target's on-chip debug port can be reached, identifying the silicon vendor from DPIDR/IDCODE, and confirming halt+memory…