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 skills/maxandersen/skills/bytemannpx skills add maxandersen/skills --skill bytemangit clone --depth 1 https://github.com/maxandersen/skillsWrote 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/maxandersen/skills/byteman)<a href="https://agentmods.dev/skills/maxandersen/skills/byteman"><img src="https://agentmods.dev/badge/skills/maxandersen/skills/byteman.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 | $0.00047 | $0.03764 |
| Opus 5 | $0.00023 | $0.01882 |
| Sonnet 5 | $0.00009 | $0.00753 |
| Haiku 4.5 | $0.00005 | $0.00376 |
Grade A, and why
byteman 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 4d 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 — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Byteman — Runtime Java Code Injection
Overview
Byteman is a Java agent that injects code into running applications without recompiling. Use it to:
- Trace method calls, arguments, return values
- Read private fields, internal state
- Mutate state — change field values, force return values, throw exceptions
- Verify behavior — assert methods were called, check ordering
- Debug production-like issues — simulate failures, delays, race conditions
Announce at start: "I'm using the byteman skill to inject diagnostic/mutation code into the Java process."
Setup via JBang
No manual Byteman download needed. JBang has a Byteman catalog that handles everything — agent JAR resolution, classpath, boot classpath — all via --javaagent.
The Key Pattern
# Run ANY jar/artifact/script with Byteman attached:
jbang --javaagent=byteman@bytemanproject myapp.jar
jbang --javaagent=byteman@bytemanproject org.group:artifact:version
jbang --javaagent=byteman@bytemanproject alias@catalog
# With a Byteman rule script:
jbang --javaagent=byteman@bytemanproject=script:rules.btm myapp.jar
# With a REMOTE rule script (jbang 0.104+):
jbang --javaagent=byteman@bytemanproject=script:%{https://url/to/rules.btm} myapp.jar
# With boot classpath (needed for injecting into JDK classes):
jbang --javaagent=byteman@bytemanproject=boot:$(jbang info classpath byteman@maxandersen),script:rules.btm myapp.jar
That's it. No BYTEMAN_HOME, no manual JAR downloads, no java -javaagent:... wrangling. JBang resolves Byteman, installs Java if needed, and runs everything.
For Non-JBang Use (manual JAR path)
If you need the raw JAR path for use with plain java or Maven:
BYTEMAN_JAR=$(jbang info classpath org.jboss.byteman:byteman:4.0.25)
Byteman Rule Syntax
Byteman rules are written in .btm files using a simple DSL:
RULE <descriptive name>
CLASS <fully.qualified.ClassName> # or INTERFACE for interface methods
METHOD <methodName>[(parameter types)] # optional parameter types for overloads
AT <location> # WHERE to inject (see locations below)
HELPER <helper class> # optional, defaults to org.jboss.byteman.rule.helper.Helper
BIND <variable bindings> # optional, bind variables for use in conditions/actions
IF <condition> # guard condition (use TRUE for always)
DO <action> # what to do
ENDRULE
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.
- 4d ago First seen · 457 lines · 47 tokens per session scan A 2d63b25f6211
byteman is a skill published in the GitHub repository maxandersen/skills (2 stars, last pushed 19d ago), licensed MIT. It adds 47 tokens to every session and 3,764 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…