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 rules/one3qualsone/elastic-security-agent-mesh/project-contextgit clone --depth 1 https://github.com/one3qualsone/elastic-security-agent-meshWrote 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/rules/one3qualsone/elastic-security-agent-mesh/project-context)<a href="https://agentmods.dev/rules/one3qualsone/elastic-security-agent-mesh/project-context"><img src="https://agentmods.dev/badge/rules/one3qualsone/elastic-security-agent-mesh/project-context.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 | $0.00752 | $0.00752 |
| Opus 5 | $0.00376 | $0.00376 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
project-context 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elastic Security Agent Mesh
Multi-agent autonomous SOC built natively on Elastic (Agent Builder + Workflows + Elasticsearch). Agents are domain specialists that discover each other via a shared agent-registry index and collaborate through investigation-contexts.
Architecture (4 + 2 Layers)
- Orchestrator — routes user/alert requests to specialists via semantic search on
agent-registry - Specialist Agents — Detection Engineering, Threat Intelligence, L1 Triage Analyst, L2 Investigation Analyst, Forensics, Compliance, SOC Operations (each in
agents/definitions/) - Shared Tool Workflows — reusable YAML workflows in
workflows/(enrichment, search, cases, alerts, endpoint, VirusTotal) - Knowledge Management —
kb-*indices withsemantic_textfields; CRUD viaworkflows/knowledge/ - Investigation Context —
investigation-contextsindex tracks shared state across multi-agent investigations (workflows/investigation/) - Governance —
action-policiesindex with tiered risk controls; checked before high-impact actions (workflows/governance/)
Read ROADMAP.md before making structural changes.
File Conventions
- Agent definitions:
agents/definitions/{name}.yaml(reference configs, not executable workflows) - Setup workflows:
agents/setup/(index creation, agent registration) - Tool workflows:
workflows/{category}/{name}.yaml - Mesh-only:
workflows/mesh/,workflows/investigation/,workflows/governance/,agents/ - Open-sourceable: everything in
workflows/exceptmesh/,investigation/,governance/
Workflow YAML Patterns
- Required fields:
name,steps; optional:description,tags,triggers,consts,inputs,outputs - Step types:
console,http,elasticsearch.search,elasticsearch.index,elasticsearch.request,kibana.request,kibana.cases,kibana.post_agent_builder_converse,foreach,parallel,wait,if - Variables:
{{ consts.x }},{{ inputs.x }},{{ steps.step_name.output.x }}, Liquid templating - Secrets go in
constswith placeholder values; real values in environment variables (never committed)
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.
- 4d ago First seen · 71 lines · 752 tokens per session scan A 0b401993c470
project-context is a cursor rule published in the GitHub repository one3qualsone/elastic-security-agent-mesh (12 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 752 tokens to every session, about $0.0038 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.