tinkermonkey/rounds-investigate
.claude/skills/rounds-investigate/SKILL.md
Investigate a distributed trace by ID — fetches the full trace, reads source files, and explains the end-to-end code flow
development
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add tinkermonkey/rounds rounds-investigateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 2:48 PM113.5s1 file scanned
SKILL.md
- name:
- rounds-investigate
- description:
- Investigate a distributed trace by ID — fetches the full trace, reads source files, and explains the end-to-end code flow
- user_invocable:
- true
- args:
- [trace_id]
Rounds: Investigate Trace
Investigate a distributed trace using rounds' trace investigation pipeline. Fetches the full trace from the telemetry backend, reads the relevant source files from the mounted codebase, and explains the end-to-end code flow with actual file:line citations.
Usage
/rounds-investigate TRACE_ID
TRACE_ID is a 32-char lowercase hex OpenTelemetry trace ID, e.g.:
d5b99e396c3aeac81aa6074635254687
Implementation
Run the following, substituting $ARGUMENTS for the trace ID:
cd /workspace/rounds && python -m rounds.main cli-run investigate-trace $ARGUMENTS
The command outputs a JSON object. Parse it and present the results as follows:
On success ("status": "success"):
- Summary — the
investigation.summaryfield as a clear paragraph - Code Flow —
investigation.code_flowas a numbered list; each entry is a step in the request path - Services Involved —
investigation.services_involvedas a comma-separated list - Key Findings —
investigation.key_findingsas a bulleted list - Cost —
investigation.cost_usdformatted as$X.XXXX
On error ("status": "error"):
Show the message field and suggest:
- Verify the trace ID is a valid 32-char lowercase hex string
- Check that the telemetry backend (SigNoz/Jaeger) is reachable from the container
- Confirm
CODEBASE_PATH=/workspace/targetis set and the target is mounted
Example
/rounds-investigate d5b99e396c3aeac81aa6074635254687
Related Skills
tinkermonkey/rounds-test
testing
VerifiedTrustedCommunity
Run pytest with coverage and display results
SKILL.mdUpdated Apr 16, 2026
tinkermonkey/rounds-resolve
devops
VerifiedTrustedCommunity
Mark a rounds error signature as resolved after a fix has been deployed
SKILL.mdUpdated Apr 16, 2026
tinkermonkey/rounds-reinvestigate
data-ai
VerifiedTrustedCommunity
Re-run LLM diagnosis for an existing rounds error signature
SKILL.mdUpdated Apr 16, 2026
tinkermonkey/.claude/skills/rounds-patterns
development
VerifiedTrustedCommunity
--- name: rounds-patterns description: Show common coding patterns: frozen dataclasses, async ports, immutable collections user_invocable: true args: generated: true generation_timestamp: 2026-02-13T22:09:52.359861Z generation_version: "2.0" source_project: rounds source_codebase_hash: a44338f108beaf54 --- # Rounds Coding Patterns Quick-reference skill for **rounds** project coding patterns and conventions. ## Usage ```bash /rounds-patterns ``` ## Purpose Displays the core coding patterns
SKILL.mdUpdated Apr 16, 2026