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/wb04307201/methodtracelog/claude-mdgit clone --depth 1 https://github.com/wb04307201/methodTraceLogWrote 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/wb04307201/methodtracelog/claude-md)<a href="https://agentmods.dev/instructions/wb04307201/methodtracelog/claude-md"><img src="https://agentmods.dev/badge/instructions/wb04307201/methodtracelog/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 | $0.07342 | $0.07342 |
| Opus 5 | $0.03671 | $0.03671 |
| Sonnet 5 | $0.01468 | $0.01468 |
| Haiku 4.5 | $0.00734 | $0.00734 |
Grade A, and why
methodTraceLog 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 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this project is
methodTraceLog is a Spring Boot starter that wraps application code with a method-tracing AOP aspect. For every intercepted method it emits a ServiceCallInfo (traceid / spanid / pspanid, class, signature, args, return value or exception, action enum, timestamp) which is then fanned out to a list of ICallService beans. Two are built in: one writes a structured log line, the other records Micrometer Timer samples and builds a parent/child MethodTraceInfo tree that the web panel renders. A second feature, gated by method-trace-log.file.enable, reads/parses log files via NIO WatchService and tail-pushes new lines over STOMP to /topic/log-monitor. The decompiler (DecompilerUtils, CFR-backed) is exposed as an HTTP endpoint at GET /methodTraceLog/decompile, gated by an optional X-Api-Key filter.
A companion module methodTraceLog-mcp is a separate, standalone Spring Boot process that speaks Model Context Protocol over stdio and forwards @Tool calls to one or more hosts (each host is a separate app that has the starter on the classpath) over HTTP. This is how AI agents get access to the trace / log / decompile data without bringing in any AI framework themselves.
The published artifact is com.gitee.wb04307201.methodTraceLog:methodTraceLog-spring-boot-starter. The working tree builds 1.0-SNAPSHOT.
Build, test, run
Maven multi-module project, Java 17. Run from the repo root.
- Build everything and install into the local repo:
mvn install - Build/test a single module and its dependencies:
mvn -pl methodTraceLog-test -am package - Run all tests:
mvn test - Run a single test class:
mvn -pl methodTraceLog-test test -Dtest=AbstractCallServiceTest - Run a single test method:
mvn -pl methodTraceLog-test test -Dtest=AbstractCallServiceTest#transContext_withArray_shouldConvertToList - Launch the sample app:
mvn -pl methodTraceLog-test spring-boot:run. The test module declaresspring-boot-maven-plugin(added in earlier rounds);mvn packageproduces an executable fat-jar atmethodTraceLog-test/target/methodTraceLog-test-1.0-SNAPSHOT.jarthat can be run withjava -jar. - Launch the MCP server:
java -jar methodTraceLog-mcp/target/methodTraceLog-mcp-1.0-SNAPSHOT.jar(talks over stdio). - The Maven
mvncommand on this machine must be invoked via/c/developer/apache-maven-3.9.16/bin/mvn(the defaultmvnshim is broken).
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 · 207 lines · 7,342 tokens per session scan A 7ffbb871a27f
methodTraceLog CLAUDE.md is an instructions file published in the GitHub repository wb04307201/methodTraceLog (47 stars, last pushed 5d ago), licensed Apache-2.0. It adds 7,342 tokens to every session, about $0.0367 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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.