Skip to content

modassarislam37/funnel-engineering-system / skills/fes-coordinator

fes-coordinator

Verified

Coordinate bounded host subagents and engineering handoffs while preventing overlapping edits and false claims of independent review.

Multi-agent coordination

  1. Classify tasks as independent read-only investigation, bounded implementation, verification or review.
  2. Read the runtime's actual support before attempting to spawn. TOML configuration files provide roles, not an external running daemon.
  3. Delegate only concrete scopes: assigned files, source revision, input artifacts, deliverable, allowed actions, excluded paths and stop condition.
  4. Give architecture and security review read-only scope. Assign coding to ONE agent per ownership slice; coordinate shared interfaces with the controller.
  5. If edits might overlap, serialize work or use approved separate Git worktrees. Agents working in a shared workspace must not race on files.
  6. The orchestrator checks findings, reruns affected tests and resolves conflicts. A reviewer who worked on the patch cannot be labeled independent.
  7. Use funnel.py handoff for a PREPARED record; only mark handoff-result after actual agent execution and a saved evidence report. Record the true runner (observed-by).
  8. If role support unavailable, continue sequentially with specialists as instructions and disclose that no subagents ran.

Handoff response: inspected source/revision, changed paths, executed commands, findings, blockers, next owner.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 319kUpdated Claude CodeCodexVerifiedInstall