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 instructions/opensearch-project/security/agents-mdgit clone --depth 1 https://github.com/opensearch-project/securityWhat 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 | $0.02147 | $0.02147 |
| Opus 5 | $0.01073 | $0.01073 |
| Sonnet 5 | $0.00429 | $0.00429 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
security AGENTS.md 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 2d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — OpenSearch Security Plugin
Guidance for AI coding agents working in this repository.
Keeping This File Up to Date
This file should be updated automatically as part of any change that affects the information documented here. Do not treat it as a separate maintenance task — include the AGENTS.md update in the same commit or PR as the relevant code change. Examples of changes that should trigger an update:
- Adding, removing, or renaming source packages or top-level directories
- Changing the build system, required JDK version, or key Gradle tasks
- Adding or retiring test suites or testing conventions
- Changing code style tooling or static analysis configuration
- Updating contribution workflows (branching strategy, backport process, commit conventions, etc.)
- Adding new security-specific patterns or constraints agents should be aware of
When in doubt, update the file.
Repository Overview
OpenSearch Security is a plugin that adds authentication, authorization, TLS encryption, audit logging, and multi-tenancy to OpenSearch. The plugin intercepts all requests at the REST and transport layers before they reach OpenSearch action handlers.
See ARCHITECTURE.md for detailed flow diagrams.
Repository Structure
src/
main/java/org/opensearch/security/
action/ # Custom OpenSearch actions registered by the plugin
auditlog/ # Audit and compliance logging framework
auth/ # Authentication backends (basic, PKI, proxy, LDAP, Kerberos, JWT, OIDC, SAML)
authtoken/ # On-behalf-of (OBO) token issuance for extensions
compliance/ # Field-level security and compliance (GDPR/HIPAA/PCI/SOX) features
configuration/ # Security index management, config hot-reload
dlic/ # Dynamic configuration REST API (roles, users, role-mappings, etc.)
filter/ # REST and transport request/response filter pipeline
hasher/ # Password hashing utilities
http/ # HTTP/HTTPS layer integration
httpclient/ # Internal HTTP client for auth backend calls
identity/ # Subject and identity abstractions
opensaml/ # OpenSAML integration utilities
privileges/ # Authorization engine (role evaluation, DLS/FLS)
queries/ # DLS query building
resources/ # Resource sharing and access control
rest/ # REST action handlers and route registration
securityconf/ # Security configuration model (roles, mappings, users)
setting/ # Plugin settings definitions
ssl/ # TLS configuration for transport and HTTP layers
state/ # Cluster security state management
support/ # Shared support utilities
tools/ # Admin tools (securityadmin)
transport/ # Transport layer interception and enforcement
user/ # User model and attribute handling
util/ # General utilities
test/ # Unit tests
integrationTest/ # Integration tests (require a running OpenSearch cluster)
spi/ # Security Plugin Interface — public extension points for other plugins
libs/
opensaml/ # Vendored/shaded OpenSAML library
sample-resource-plugin/ # Example plugin using the resource-sharing SPI
config/ # Default demo configuration (certs, roles, users, mappings)
tools/ # Shell scripts: securityadmin.sh, install_demo_configuration.sh
scripts/ # CI/CD helper scripts
bwc-test/ # Backwards-compatibility tests
checkstyle/ # Checkstyle rule configuration
formatter/ # Eclipse JDT formatter configuration
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.
- 2d ago First seen · 221 lines · 2,147 tokens per session scan A 7b0449e04df5
security AGENTS.md is an instructions file published in the GitHub repository opensearch-project/security (252 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,147 tokens to every session, about $0.0107 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.