Explicit Identity Across Boundaries
Install
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill explicit-identitySKILL.md
Explicit Identity Across Boundaries
Never rely on "latest" or "current" when crossing process or async boundaries.
Pattern
Pass explicit identifiers through the entire pipeline. "Most recent" is a race condition.
DO
- Pass
--session-id $IDwhen spawning processes - Store IDs in state files for later correlation
- Use full UUIDs, not partial matches
- Keep different ID types separate (don't collapse concepts)
DON'T
- Query for "most recent session" at execution time
- Assume the current context will still be current after await/spawn
- Collapse different ID types:
session_id= Claude Code session (human-facing)root_span_id= Braintrust trace (query key)turn_span_id= Braintrust turn within session
Example
// BAD: race condition at session boundaries
spawn('analyzer', ['--learn']) // defaults to "most recent"
// GOOD: explicit identity
spawn('analyzer', ['--learn', '--session-id', input.session_id])
Source Sessions
- 1c21e6c8: Defined session_id vs root_span_id distinction
- 6a9f2d7a: Fixed wrong-session attribution via explicit passing
- a541f08a: Confirmed pattern prevents race at session boundaries
Related skills
find-skillsvercel-labs3.6MHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.handoffmattpocock883KCompact the current conversation into a handoff document for another agent to pick up.microsoft-foundrymicrosoft618KBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, agent insights, pull agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agcavemanjuliusbrussee544KUltra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
