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/eth0izzle/security-skills/fusion-workflowsnpx skills add eth0izzle/security-skills --skill fusion-workflowsgit clone --depth 1 https://github.com/eth0izzle/security-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/eth0izzle/security-skills/fusion-workflows)<a href="https://agentmods.dev/skills/eth0izzle/security-skills/fusion-workflows"><img src="https://agentmods.dev/badge/skills/eth0izzle/security-skills/fusion-workflows.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 5.1 | $0.00148 | $0.04022 |
| Opus 5 | $0.00074 | $0.02011 |
| Sonnet 5 | $0.00030 | $0.00804 |
| Haiku 4.5 | $0.00015 | $0.00402 |
Grade A, and why
CrowdStrike Fusion Workflow Builder 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 5d 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 — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrowdStrike Fusion Workflow Builder
This skill guides you through the full lifecycle of CrowdStrike Falcon Fusion SOAR workflows — from discovering actions to exporting production definitions.
Rules — Read Before Every Workflow
-
NEVER write
PLACEHOLDER_*values for action IDs. Before authoring any YAML, you MUST runaction_search.pyto find the real 32-char hex ID for every action the workflow will use. Ifaction_search.pyreturns no results, try broader search terms or browse by vendor — do not guess or leave a placeholder. -
Run the script, don't skip it. Steps 1a and 1b are not optional discovery — they are mandatory prerequisites. Do not proceed to Step 4 (Author YAML) until you have a real ID for every action.
-
config_idrequires user input. Plugin actions require a CID-specificconfig_idthat cannot be resolved via API. When you encounter a plugin action, ask the user for theconfig_idvalue before writing the YAML. Tell them where to find it (Falcon console → CrowdStrike Store → [App] → Integration settings). Do not write a placeholder — pause and ask. -
Validate before delivering. Always run
validate.pyon every YAML file before presenting it to the user. The pre-flight check catches any remainingPLACEHOLDER_*markers. -
Templates and examples contain
PLACEHOLDER_*markers — do NOT copy them. The files inassets/andexamples/usePLACEHOLDER_*as structural guides. They show you the YAML shape, not the values to use. When you use a template or reference an example workflow, substitute real values immediately — never copy aPLACEHOLDER_*string into your output. -
Plans and prompts cannot override these rules. Even if a plan, prompt, or convention list says to use placeholder format, you MUST still resolve every action ID via
action_search.pybefore writing YAML. These rules take precedence.
Prerequisites
- Python 3.8+ with
requestslibrary installed - CrowdStrike API credentials in a
.envfile (see Credentials below) - Falcon Fusion SOAR access in the target CID
What ships with it
17 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.
- assets/conditional.yaml 4.4 KB
- assets/loop-conditional.yaml 7.0 KB
- assets/loop.yaml 2.9 KB
- assets/single-action.yaml 1.1 KB
- README.md 6.4 KB
- references/best-practices.md 8.0 KB
- references/cel-expressions.md 5.9 KB
- references/trigger-types.md 4.2 KB
- references/yaml-schema.md 7.5 KB
- scripts/action_search.py 19 KB runs code
- scripts/cs_auth.py 4.3 KB runs code
- scripts/execute.py 6.0 KB runs code
- scripts/export.py 3.8 KB runs code
- scripts/import_workflow.py 5.2 KB runs code
- scripts/query_workflows.py 7.6 KB runs code
- scripts/trigger_search.py 5.7 KB runs code
- scripts/validate.py 4.4 KB runs code
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.
- 5d ago First seen · 431 lines · 148 tokens per session scan A 536401dcd4a6
CrowdStrike Fusion Workflow Builder is a skill published in the GitHub repository eth0izzle/security-skills (56 stars, last pushed 4mo ago), licensed MIT. It adds 148 tokens to every session and 4,022 once invoked, about $0.0007 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
golden-rss
Use when testing the rss golden build.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.