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/btraceio/btrace/claude-mdgit clone --depth 1 https://github.com/btraceio/btraceWhat 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 | $0.00451 | $0.00451 |
| Opus 5 | $0.00226 | $0.00226 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
btrace CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Claude Code Guide
Follow the repository-wide rules in AGENTS.md. This file intentionally contains only Claude-specific orientation; AGENTS.md is the canonical operational contract.
Common commands
Use a workspace-local Gradle cache when appropriate, and redirect Gradle output to a log before filtering and reading it (see AGENTS.md).
# Distribution and all unit tests
GRADLE_USER_HOME=$(pwd)/.gradle-user ./gradlew :btrace-dist:build
# Module, test class, or formatting check
GRADLE_USER_HOME=$(pwd)/.gradle-user ./gradlew :btrace-agent:test
GRADLE_USER_HOME=$(pwd)/.gradle-user ./gradlew :btrace-agent:test --tests '*InstrStackTest'
GRADLE_USER_HOME=$(pwd)/.gradle-user ./gradlew spotlessCheck
# Integration tests: build the distribution first
GRADLE_USER_HOME=$(pwd)/.gradle-user ./gradlew -Pintegration :integration-tests:test
# Intentional instrumentation-bytecode changes only
GRADLE_USER_HOME=$(pwd)/.gradle-user ./gradlew test -PupdateTestData
Where to look
- Script compiler and verifier:
btrace-compiler - Agent lifecycle and bytecode weaving:
btrace-agent(instrumentation engine lives in itsio.btrace.instrpackage) - Script API, runtime, and protocol:
btrace-core,btrace-runtime - CLI:
btrace-client; packaging:btrace-dist - Golden instrumentation data:
btrace-agent/src/test/resources/instrumentorTestData/
Detailed references
- Documentation index
- Masked JAR architecture — required reading for distribution/class-loading changes
- Instrumentation backends
- Protocol architecture
- Extension development
- Troubleshooting
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 · 41 lines · 451 tokens per session scan A 783125287985
btrace CLAUDE.md is an instructions file published in the GitHub repository btraceio/btrace (5,992 stars, last pushed today), licensed Apache-2.0. It adds 451 tokens to every session, about $0.0023 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
dotnet-dump-mcp AGENTS.md
Instructions for frankbolero/dotnet-dump-mcp, covering claude.md, project summary, build, test, and development commands, core development and build the solution.
PerfGraph AGENTS.md
Instructions for Be1zebub/PerfGraph, covering perfgraph — ai agent instructions, what perfgraph is, how ai agents should use perfgraph, quick entry point and mcp mode (for ai agents with mcp support).
ros2_medkit_mcp copilot-instructions.md
Copilot instructions for selfpatch/ros2_medkit_mcp, covering copilot instructions, project overview, architecture, key components and sovdclient (client.py).
obd-mcp-server AGENTS.md
AGENTS.md instructions for ayhammouda/obd-mcp-server, covering repository instructions, non-negotiable safety rules, data and licensing rules, network and runtime rules and required checks.
health-monitor-mcp copilot-instructions.md
Copilot instructions for oaslananka/health-monitor-mcp, covering github copilot instructions, expectations, validation and output quality.
debug-recorder-mcp AGENTS.md
AGENTS.md instructions for oaslananka/debug-recorder-mcp, a project described as: TypeScript MCP server for structured debug session capture, reproducible diagnostics, event recording, and developer workflow observability.