From beads
Logs agent interactions (prompts, responses, tool calls) to append-only .beads/interactions.jsonl. Also supports labeling prior entries via record|label args.
npx claudepluginhub gastownhall/beads --plugin beadsrecord|labelAppend-only audit logging for agent interactions (prompts, responses, tool calls) in `.beads/interactions.jsonl`. Each line is one event. Labeling is done by appending a new `"label"` event referencing a previous entry. ## Usage - **Record an interaction**: - `bd audit record --kind llm_call --model "claude-3-5-haiku" --prompt "..." --response "..."` - `bd audit record --kind tool_call --tool-name "go test" --exit-code 1 --error "..." --issue-id bd-42` - **Pipe JSON via stdin**: - `cat event.json | bd audit record` - **Label an entry**: - `bd audit label int-a1b2 --label good -...
/auditAudits UI code against design system for spacing, depth, color, and pattern violations. Reports file-specific issues and suggestions. Supports path argument or defaults to common UI paths.
/auditPerforms security audit of codebase for dependency vulnerabilities, secrets, OWASP Top 10, input validation, auth issues, and misconfigs. Outputs findings report by severity with fixes and references.
/auditRuns Rust security audits (default) with cargo audit and geiger, or safety/concurrency/full modes using miri, rudra, lockbud. Outputs prioritized vulnerability reports and fix recommendations.
/auditAnalyzes iOS/Swift projects to suggest relevant audits or runs specified ones (e.g., memory, concurrency, accessibility, SwiftUI performance, security).
/auditPerforms security audit on codebase or specified target, checking dependency vulnerabilities, auth, input validation, data exposure, configs, and secrets. Outputs prioritized findings with remediation steps.
/auditPerforms security audit on codebase or specified target, checking dependency vulnerabilities, auth, input validation, data exposure, configs, and secrets. Outputs prioritized findings with remediation steps.
Append-only audit logging for agent interactions (prompts, responses, tool calls) in .beads/interactions.jsonl.
Each line is one event. Labeling is done by appending a new "label" event referencing a previous entry.
Record an interaction:
bd audit record --kind llm_call --model "claude-3-5-haiku" --prompt "..." --response "..."bd audit record --kind tool_call --tool-name "go test" --exit-code 1 --error "..." --issue-id bd-42Pipe JSON via stdin:
cat event.json | bd audit recordLabel an entry:
bd audit label int-a1b2 --label good --reason "Worked perfectly"bd audit label int-a1b2 --label bad --reason "Hallucinated a file path"bd dolt push includes .beads/interactions.jsonl in the commit allowlist.