BTrace is a Java diagnostic tool that dynamically inserts tracing into running Java applications without restarting or recompiling them. Java developers and operations teams use it to inspect methods, timings, fields, allocations, and other runtime behavior in production environments. Catalogue add-ons provide instructions for using BTrace.
Borrowing it
Nothing to install: this file belongs to btraceio/btrace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/btraceio/btrace/develop/.claude/skills/steward/SKILL.mdgit clone --depth 1 https://github.com/btraceio/btraceWrote 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/skills/btraceio/btrace/steward)<a href="https://agentmods.dev/skills/btraceio/btrace/steward"><img src="https://agentmods.dev/badge/skills/btraceio/btrace/steward/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/btraceio/btrace/steward"><img src="https://agentmods.dev/badge/skills/btraceio/btrace/steward.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.00963 |
| Opus 5.5 | $0.00022 | $0.00385 |
| Sonnet 5.5 | $0.00011 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
steward 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 3d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stewarding a BTrace pull request
Repository rules in AGENTS.md apply throughout; this file adds only what is specific to driving a PR.
Branches and merging
- PRs target
develop. They are squash-merged, so the PR title becomes the commit subject: use a Conventional Commits title (fix(agent): ...,build: ...,chore(deps): ...). - On a branch you created, bring
developin with a merge commit once the PR is open; do not force-push a branch a reviewer has already looked at.
Before every push
- Run what the change can affect:
spotlessCheckand the changed modules' tests, with output redirected to a log as AGENTS.md describes. - Configuring the root build needs a JDK 8 toolchain (
common.gradleresolves it eagerly), andbtrace-agentneeds a JDK 24 toolchain to compile itsjava24source set and a JDK 28 launcher forclassFileApiBackendTest, whichcheckdepends on. If a required JDK is unavailable locally, Gradle cannot verify the change: say so in the PR's Testing section instead of ticking the box, and treat the PR's CI as the check. - Golden instrumentation data in
btrace-agent/src/test/resources/instrumentorTestData/is regenerated only with./gradlew test -PupdateTestData, and only for an intentional instrumentation change. Never edit it by hand, and never regenerate it to make an unexplained diff go away.
CI triage
spotlessCheckfailing on files the PR did not touch means the formatter changed, not the code. An unpinnedgoogleJavaFormat()ingradle/spotless.gradlefollows the Spotless plugin's default, so a Spotless bump can move it; check whether the formatter pin or the Spotless plugin version moved before runningspotlessApplyacross the tree.Cannot find a Java installation ... matching: {languageVersion=N}means a workflow no longer installs a JDK the build needs. Thesetup-javasteps in.github/workflows/are toolchain requirements (JDK 24 feedsbtrace-agent'sjava24source set); restore the step rather than changing the build.- JUnit resolving a JDK 17+ artifact for a JVM 8 configuration means the JUnit 5.14.4 pin was bumped.
btrace-agentandintegration-testscompile tests with a JDK 8 javac, andbtrace-gradle-pluginkeeps Java 8-compatible test dependencies; the pin is intentional. - Maven Central can answer
429 Too Many Requestsduring dependency resolution. That is an infrastructure failure: one re-run is justified; a second identical failure needs reporting, not more re-runs.
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.
- 3d ago First seen · 42 lines · 56 tokens per session scan A 4dcf4e7cfa6d
steward is a skill published in the GitHub repository btraceio/btrace (5,997 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 963 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
meta-pre-commit-quality-gate
Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.
verify-commit
Verify that commits for a GitHub issue include tests and that those tests fail without the implementation changes. Given an issue ID, finds commits, checks for test files, then reverts src/main changes and runs the tests to confirm they fail.
verify-akashic-plugin
A plugin acceptance skill that commits a plugin, installs it into the running application, checks its status, and uses it once to confirm whether it works.
Changelog Test Mapper
Map changelog entries and release notes to affected test cases, ensuring every user-facing change has corresponding test coverage verification.