Elastic Agent Skills is a library of instruction packages that teach AI coding agents how to work with Elastic products, including Elasticsearch, Kibana, Elastic Observability, and Elastic Security. Developers use the skills for tasks such as API work, Kibana content management, observability, and security workflows. The catalogue entries are skills and plugins from this library.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/elastic/agent-skillsnpx agentmods add skills/elastic/agent-skills/detection-rule-managementWrote 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/elastic/agent-skills/detection-rule-management)<a href="https://agentmods.dev/skills/elastic/agent-skills/detection-rule-management"><img src="https://agentmods.dev/badge/skills/elastic/agent-skills/detection-rule-management/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/elastic/agent-skills/detection-rule-management"><img src="https://agentmods.dev/badge/skills/elastic/agent-skills/detection-rule-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 155 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 47 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Tool Misuse · line 155 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00043 | $0.03504 |
| Opus 5 | $0.00022 | $0.01752 |
| Sonnet 5 | $0.00009 | $0.00701 |
| Haiku 4.5 | $0.00004 | $0.00350 |
Grade A, and why
security-detection-rule-management 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- security-detection-rule-management — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection Rule Management
Create new detection rules for emerging threats and coverage gaps, and tune existing rules to reduce false positives.
All operations use the Kibana Detection Engine API via rule-manager.js.
Execution rules
- Start executing tools immediately — do not read SKILL.md, browse the workspace, or list files first.
- Report tool output faithfully. Copy rule IDs, names, alert counts, exception IDs, and error messages exactly as returned by the API. Do not abbreviate rule UUIDs, invent rule names, or round alert counts.
- When a tool returns an error (rule not found, API failure), report the exact error — do not guess at alternatives.
Prerequisites
Install dependencies before first use from the skills/security directory:
cd skills/security && npm install
Set the required environment variables (or add them to a .env file in the workspace root):
export ELASTICSEARCH_URL="https://your-cluster.es.cloud.example.com:443"
export ELASTICSEARCH_API_KEY="your-api-key"
export KIBANA_URL="https://your-cluster.kb.cloud.example.com:443"
export KIBANA_API_KEY="your-kibana-api-key"
Common multi-step workflows
| Task | Tools to call (in order) |
|---|---|
| Tune noisy SIEM rule | rule_manager find/noisy-rules → run_query (investigate FPs) → rule_manager patch or add-exception |
| Add endpoint behavior exception | fetch_endpoint_rule (get rule definition from GitHub) → add_endpoint_exception (scoped to rule.id) |
| Create new detection rule | run_query (test query against data) → rule_manager create |
| Investigate rule alert volume | rule_manager get → run_query (query alerts index) |
What ships with it
10 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.
- references/detection-api-reference.md 7.9 KB
- references/endpoint-behavior-tuning-workflow.md 6.3 KB
- references/endpoint-exceptions-guide.md 3.8 KB
- references/endpoint-rule-exclusion-best-practices.md 6.3 KB
- scripts/add-endpoint-exception.js 5.5 KB runs code
- scripts/check-exclusion-best-practices.js 2.1 KB runs code
- scripts/es-client.js 1.8 KB runs code
- scripts/fetch-endpoint-rule-from-github.js 3.8 KB runs code
- scripts/kibana-client.js 6.7 KB runs code
- scripts/rule-manager.js 21 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.
- 9d ago First seen · 287 lines · 43 tokens per session scan A 1091af20e817
security-detection-rule-management is a skill published in the GitHub repository elastic/agent-skills (571 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 3,504 once invoked, about $0.0002 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…