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/themoah/klag/claude-mdgit clone --depth 1 https://github.com/themoah/klagWrote 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/themoah/klag/claude-md)<a href="https://agentmods.dev/instructions/themoah/klag/claude-md"><img src="https://agentmods.dev/badge/instructions/themoah/klag/claude-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 | $0.05954 | $0.05954 |
| Opus 5 | $0.02977 | $0.02977 |
| Sonnet 5 | $0.01191 | $0.01191 |
| Haiku 4.5 | $0.00595 | $0.00595 |
Grade A, and why
klag CLAUDE.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 today.
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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Klag is a Kafka Lag Exporter built with Vert.x 4.5.30. Monitors consumer lag and group states with Prometheus/Datadog/OTLP metrics.
Build Commands
# Requires Java 21 - use SDKMAN if needed: sdk use java 21.0.9-tem
# Local: use ./gradlew | CI: uses gradle directly (no wrapper JAR committed)
./gradlew compileJava # Compile
./gradlew test # Run tests
./gradlew assemble # Package (creates fat JAR)
./gradlew run # Run with hot-reload
./scripts/test-helm-chart.sh # Helm chart template tests (offline)
./scripts/e2e-test.sh # Full e2e: k3d + real Kafka + chart + lag asserts
./scripts/e2e-strimzi-test.sh # e2e against Strimzi-operator-managed Kafka (KRaft)
./scripts/e2e-strimzi-matrix.sh # Strimzi e2e across supported Kafka versions
GraalVM Native Image (startup/memory optimized)
Requires a GraalVM JDK 21 (LTS) with native-image (e.g. sdk install java 21.0.2-graalce).
Run Gradle with that JDK as JAVA_HOME/GRAALVM_HOME.
gradle nativeCompile # -> build/native/nativeCompile/klag (standalone binary)
docker build -f Dockerfile.native -t klag:native . # distroless runtime image
scripts/benchmark-startup.sh native - build/native/nativeCompile/klag # startup/RSS bench
Native config lives in build.gradle.kts (graalvmNative block) plus reachability
hints in src/main/resources/META-INF/native-image/. Reflection metadata for Netty,
kafka-clients, logback and micrometer comes from the GraalVM Reachability Metadata
Repository (auto-enabled). Entry point is KlagLauncher (direct new MainVerticle(),
no reflective Vert.x launcher).
Measured (macOS arm64, prometheus reporter, Kafka up): native ≈ 70-100 ms startup / 44 MB RSS vs JVM 21 ≈ 470-520 ms / 119 MB. JVM 25 (LTS) showed no startup/memory gain over 21 for this workload (slightly higher RSS), so the runtime stays on JDK 21.
Architecture
Vert.x reactive framework with Future<T>-based async API.
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.
- today Changed · +33 lines · +780 tokens per session 1550b10b210d
- 4d ago First seen · 286 lines · 5,174 tokens per session scan A bfb569197f7d
klag CLAUDE.md is an instructions file published in the GitHub repository themoah/klag (82 stars, last pushed 3d ago), licensed Apache-2.0. It adds 5,954 tokens to every session, about $0.0298 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
kafka-backup CLAUDE.md
Claude Code instructions for osodevops/kafka-backup, covering project overview, key problems solved, repository structure, build & test commands and build the project.
ccusage-web CLAUDE.md
Instructions for jx453331958/ccusage-web, covering claude code project memory, common issues, project structure, deployment and agent.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).