Rafi Imam

What an agent can do with the agent-capture-bench corpus

rafiimam/agent-capture-bench: Ground-truth benchmark for process capture on Linux: an independent eBPF oracle scores tracers, audit pipelines, and agent recorders…

• Look up how agent-capture-bench implements agent-auditing, audit, benchmark, with answers cited to file and line.
• Reuse a worked example: the commit “capture-evasion scenario suite, execsnoop+auditd adapters, macO…” (9 files · Python, shell).
• Answer from agent-capture-bench's real Python source instead of memory (Operations and SRE).

• How does agent-capture-bench implement agent-auditing?
• What does workflow do in agent-capture-bench?

Search the GitHub repository rafiimam/agent-capture-bench with XERJ (https://hub.xerj.org/corpus/rafiimam--agent-capture-bench).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/rafiimam/agent-capture-bench agent-capture-bench && git -C agent-capture-bench checkout d0c7f4952bab4a7418398d3e529dd19cd68f4c36
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./agent-capture-bench --url http://127.0.0.1:9200 --prefix agent-capture-bench --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus rafiimam--agent-capture-bench · Operations and SRE
Related corpora: coroot, jaeger-docs, gma1k/podtrace, ValkyrieSentinel/nox-guard
Operational intelligence with XERJ · Case study: reference coding for agents