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/redhatinsights/notifications-gw/agents-mdgit clone --depth 1 https://github.com/RedHatInsights/notifications-gwWrote 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/instructions/redhatinsights/notifications-gw/agents-md)<a href="https://agentmods.dev/instructions/redhatinsights/notifications-gw/agents-md"><img src="https://agentmods.dev/badge/instructions/redhatinsights/notifications-gw/agents-md.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 | $0.01975 | $0.01975 |
| Opus 5 | $0.00988 | $0.00988 |
| Sonnet 5 | $0.00395 | $0.00395 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
notifications-gw 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 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cross-Cutting Conventions
- Java 21, Quarkus 3.x, Maven wrapper only. Always use
./mvnw, never systemmvn. The project is a single-module Maven build with no submodules. - Package root:
com.redhat.cloud.notifications. Sub-packages areauth(identity/authentication) andmodel(DTOs shared with notifications-backend). New REST model POJOs go in the root package. - No wildcard imports.
.editorconfigsetsij_java_names_count_to_use_import_on_demand = 999to force explicit imports. - snake_case JSON, camelCase Java. Use
@JsonProperty("snake_case_name")on fields whose wire name differs from the Java name. The canonical examples areevent_type,org_id,account_id. - Config prefix: All application-specific properties use
notifications.*. Quarkus-managed properties keep their standard prefixes. Every@ConfigPropertymust have adefaultValue. - Logging: Use
io.quarkus.logging.Logstatic methods (Log.infof,Log.errorf, etc.) with%sformat placeholders. Never use SLF4J orjava.util.loggingin application code. - Metrics prefix:
notifications.gw.*for all Micrometer counters. Register counters viaMeterRegistryconstructor injection. Avoid high-cardinality tags (no org IDs or UUIDs as tag values). - CDI scope:
@ApplicationScopedeverywhere. This repo does not use@RequestScoped. REST client interfaces require both@ApplicationScopedand@RegisterRestClient. - Fault tolerance:
@Retry(maxRetries = 5)on every REST client method. No@Timeout,@CircuitBreaker, or@Fallbackin this codebase. - Response envelope: All
POST /notifications/responses use{"result":"success"}on success or{"result":"error","details":"..."}on failure, built via the privatebuildResponseEntity()helper inGwResource. Do not invent alternative shapes.
Architecture Context
This is a gateway microservice — it receives notification payloads via REST, validates them against notifications-backend, and forwards them to Kafka (platform.notifications.ingress). There is exactly one Kafka producer channel (egress) and no consumers. The gateway does not own any database or persistent state.
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 · 90 lines · 1,975 tokens per session scan A 5674ef791dd3
notifications-gw AGENTS.md is an instructions file published in the GitHub repository RedHatInsights/notifications-gw (2 stars, last pushed today), licensed Apache-2.0. It adds 1,975 tokens to every session, about $0.0099 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 2026-08-31.
Other instructions, from other repositories
awesome-copilot copilot-instructions.md
Copilot instructions for github/awesome-copilot, covering readme updates, prompt file guide, instruction file guide, agent file guide and agent skills guide.
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui helix-device-tests.instructions.md
Guidelines for running and configuring .NET MAUI device tests on Helix infrastructure.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
maui xaml-unittests.instructions.md
Guidelines for writing XAML unit tests in the Controls.Xaml.UnitTests project.
awesome-ai-apps AGENTS.md
Instructions for Arindam200/awesome-ai-apps, covering agents.md, repository overview, project categories, common development commands and running individual projects.