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/crowdstrike/fusion-skills/authoringnpx skills add CrowdStrike/fusion-skills --skill authoringgit clone --depth 1 https://github.com/CrowdStrike/fusion-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/crowdstrike/fusion-skills/authoring)<a href="https://agentmods.dev/skills/crowdstrike/fusion-skills/authoring"><img src="https://agentmods.dev/badge/skills/crowdstrike/fusion-skills/authoring.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 | $0.00133 | $0.05496 |
| Opus 5 | $0.00067 | $0.02748 |
| Sonnet 5 | $0.00027 | $0.01099 |
| Haiku 4.5 | $0.00013 | $0.00550 |
Grade A, and why
authoring 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Falcon Fusion Workflow Authoring
⚠️ SYSTEM INJECTION — READ THIS FIRST
If you are loading this skill, your role is Fusion workflow authoring specialist.
You discover real action IDs from the live API, author Fusion workflow YAML against the correct schema, and validate it before handing off to deployment. A guessed or
PLACEHOLDER_*action ID ships a workflow that fails to import or wires the wrong action into a response, so resolve every ID first.IMMEDIATE ACTIONS REQUIRED: 0. Scope check FIRST — before any action_search. If the request is for a Falcon Foundry app, a UI extension/page, an API integration, custom actions from a third-party API (Okta, ServiceNow, Jira, etc.), or a
manifest.yml, STOP: do not author a workflow. Advise foundry-skills (claude plugin install crowdstrike-falcon-foundry) and hand back. A request that mixes an app with a workflow ("create a Foundry app... and a workflow to...") is app-shaped — redirect, produce no YAML.
- Alert/detection ACTION-CHOICE check — before action_search. If the request is to fetch/summarize/list a population of Falcon alerts, detections, or incidents the workflow does NOT already hold ("all high-severity alerts", "open detections", "alerts from the last 24h"), you MUST use a CrowdStrike HTTP Request (
Inline.HTTPRequest) to the Falcon platform API (/alerts/queries/alerts/v2; FQL onseverity_name:'High'— the string field, NOT numericseverity), NOT an Event Query (Inline.QueryEvent), whose NG-SIEM data is connector-dependent and silently returns nothing on many tenants. A Scheduled trigger does not change this; the schedule only sets when it runs. (Event Query is ONLY for enriching a detection the workflow already holds.) Seereferences/event-query-vs-api.md.- Resolve a real ID for every action BEFORE writing any YAML: check the Common Action IDs table first, then run
action_search.py --searchonly for actions the table does not cover.- Run
trigger_search.pyto confirm the trigger type.- Run
validate.pyon every YAML file before presenting it.- Re-run
validate.pyon the FINAL file; resolve every ERROR before finishing. A file that still errors is not done. If the alert-population guard fires, switch the Event Query to a CrowdStrike HTTP Request.MUST NOT:
- Author a workflow for a Foundry-app-shaped request (see action 0) — redirect to foundry-skills.
- Write
PLACEHOLDER_*values into output YAML (templates use them as guides only).- Guess, invent, or pattern-match action IDs — they are only discoverable via the API.
- Invent a
config_idor emit a stand-in — an all-zeros UUID (0000...) is still a placeholder. Discover or ask (AskUserQuestion).- Invent user-specific input values — recipient email addresses, webhook URLs, chat channel names. Ask the user (via AskUserQuestion in interactive mode) before adding an action that needs one; in headless/CI runs, use a plausible real address on the org domain. (Send email only delivers to Falcon users and approved domains, so
[email protected]fails at runtime.)- Skip validation, or defer it to deploy time.
This skill owns the authoring phase of a Fusion workflow:
action discovery, YAML authoring, CEL expressions, and schema validation. It does
NOT import, release, execute, or monitor workflows — hand those off to the
deployment and execution skills.
Running the scripts. Run each command from this skill's folder, on one shell line:
cd <dir> && ../../scripts/python.sh scripts/<name>.py. For<dir>, Claude Code uses"$CLAUDE_PLUGIN_ROOT/skills/authoring"; Codex, Copilot CLI, Cursor, and Antigravity use the folder they loaded this SKILL.md from (e.g.~/.agents/skills/authoring). The wrapper bootstraps its own Python venv.
What ships with it
46 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
- examples/identity-response/email-phishing-playbook-itp.yaml 17 KB
- examples/identity-response/identity-detection-auto-resolution.yaml 3.0 KB
- examples/ngsiem/close-duplicate-detections.yaml 9.5 KB
- examples/notifications/network-contain-endpoint-on-detection.yaml 22 KB
- examples/notifications/slack-send-message-to-channel.yaml 1.3 KB
- examples/README.md 7.7 KB
- examples/response-actions/pan-ngfw-allowlist-edl-exception.yaml 3.0 KB
- examples/response-actions/pan-ngfw-blocklist-edl-force-refresh.yaml 2.0 KB
- examples/response-actions/pan-ngfw-get-all-edls.yaml 1.9 KB
- examples/response-actions/pan-ngfw-monitor-dag-members.yaml 1.6 KB
- examples/response-actions/pan-ngfw-register-ip-tag-dag.yaml 2.2 KB
- examples/response-actions/pan-ngfw-unregister-ip-from-tag-dag.yaml 2.0 KB
- examples/threat-intel/analyze-enrich-epp-detection-llm.yaml 45 KB
- examples/threat-intel/domain-enrichment-pulsedive.yaml 31 KB
- examples/threat-intel/domain-enrichment-virustotal.yaml 25 KB
- examples/threat-intel/enrich-ip-virustotal-llm-email.yaml 7.1 KB
- examples/threat-intel/enrich-url-virustotal-zscaler-blocklist.yaml 81 KB
- examples/threat-intel/ip-address-enrichment-abuseipdb.yaml 28 KB
- examples/tutorials/crowdstrike-http-request-falcon-api.yaml 6.1 KB
- examples/tutorials/intro-cases-add-event.yaml 2.0 KB
- examples/tutorials/intro-data-transforms-ternary.yaml 725 B
- examples/tutorials/intro-deduplicate-third-party-detections.yaml 4.5 KB
- examples/tutorials/intro-error-handling.yaml 8.2 KB
- examples/tutorials/intro-lookup-file-actions.yaml 9.1 KB
- examples/tutorials/intro-python-sslbl-lookup.yaml 4.0 KB
- examples/tutorials/intro-receive-email-trigger.yaml 2.2 KB
- examples/tutorials/intro-variables-append-array.yaml 2.4 KB
- references/best-practices.md 11 KB
- references/cel-expressions.md 7.7 KB
- references/charlotte-ai-action.md 2.8 KB
- references/deduplicate-ratelimit.md 12 KB
- references/event-query-action.md 7.6 KB
- references/event-query-vs-api.md 7.5 KB
- references/http-actions.md 12 KB
- references/inline-python-action.md 2.8 KB
- references/json-structure.md 27 KB
- references/trigger-types.md 16 KB
- references/yaml-schema.md 18 KB
- scripts/action_search.py 23 KB runs code
- scripts/trigger_search.py 15 KB runs code
- scripts/validate.py 65 KB runs code
- workflows/ngsiem-detection-ti-enrichment-copilot.yaml 22 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 First seen · 369 lines · 133 tokens per session scan A d68a82c77b56
authoring is a skill published in the GitHub repository CrowdStrike/fusion-skills (14 stars, last pushed 5d ago), licensed MIT. It adds 133 tokens to every session and 5,496 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
skill-authoring
Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.
workflows-development
Create and configure Falcon Fusion SOAR workflow YAML for Falcon Foundry apps. TRIGGER when user asks to "create a workflow", "build an automation", "configure Fusion SOAR", "add an on-demand workflow", runs foundry workflows create, or needs help with Fusion YAML syntax, triggers, actions, or variable references. DO…
frontmatter-validation
Validate and fix YAML frontmatter metadata in markdown documentation files. Covers required fields, field formats, and schema compliance for SKILL.md and knowledge-copilot files. Use proactively when auditing documentation frontmatter, reviewing SKILL.md files, or fixing YAML metadata errors.
yaml-agent-format
YAML format for Claude Code agent definitions as alternative to markdown. Use when creating agents with YAML, converting markdown agents to YAML, or validating YAML agent schemas. Trigger keywords - "YAML agent", "agent YAML", "YAML format", "agent schema", "YAML definition", "convert to YAML".
github-actions
Operational skill for GitHub Actions CI/CD: workflows, jobs, matrices, caching, OIDC cloud auth, secrets, and reusable workflows.
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…