Agent skill · operations · jeremylongshore
background
Use when the user wants to see, inspect, cancel, or prune background agents fired during prior chain runs. Read/manage `.hyperflow/background/registry.json` and the per-agent output buffers at `.hyperflow/background/<id>.md`. Standalone — never auto-invoked. Trigger with /hyperflow:background, "list background agents", "what's running in background", "cancel background agent", "show background result".
Why this skill is useful
Provides specific commands and workflows for managing background agents that the AI wouldn't reliably generate on its own.
What it needs
About 4k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Background Read-only-by-default management interface for background agents fired by other hyperflow skills (dispatch quality gates, deploy CI watcher, scaffold analysis refresh, cache compact, scope speculative prefetch). Reads from .hyperflow/background/registry.json + per-agent output buffers. Full doctrine: background-agents.md. Subcommands Subcommand Description --- --- list Print the registry: in-flight · completed-uncollected · stalled · errored show <id> Print one agent's output buffer (.hyperflow/background/<id>.md) cancel <id> Cancel one specific in-flight agent cancel --all Cancel every in-flight agent (use before closing a session) prune Delete completed .hyperflow/background/<id>.md files older than 7 days Default subcommand when none provided: list. Subcommand Details list Read .hyperflow/background/registry.json. Group entries by status and print a compact table: Print one trailing line: <count> in flight · <count> uncollected · <count> needs attention. If registry is empty, print No background agents. and stop. show <id> Read .hyperflow/background/<id>.md and print it verbatim. If the agent is still running, print the registry entry first then Output buffer not yet written. and stop. cancel <id> 1. Read registry, find the entry. 2. If status: running, signal cancellation per the provider's mechanism (Claude Code: use the runtime's cancellation API for that subagent ID; if unavailable, mark the entry status: cancelled and leave the agent to time out on its own — the foreground orchestrator will drop the result on collection). 3. Update registry entry: status: cancelled, cancelledat: <now>. 4. Print Cancelled <id> — <purpose>. If the agent already completed, print Agent <id> already <status> — nothing to cancel. cancel --all For every entry with status: running, run the cancel flow. Print summary: Cancelled N agents. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/background