workbench-flue-agent-harness
Workbench Flue Agent Harness
Use this skill when an issue asks to create, review, or package a deployable
Flue agent, or when it declares FLUE_AGENT_CONTRACT.
Required Source Reads
Read only as much as the task requires:
docs/flue-agent-harness-lane.mdhttps://flueframework.com/start.mdhttps://raw.githubusercontent.com/withastro/flue/refs/heads/main/README.mdhttps://flueframework.com/models.jsonif the requested model is not one of the recommended IDs
If network access is unavailable, use the checked-in workbench doc and report
FLAG unless the issue requires fresh upstream docs.
Required Contract
More from fearvox/multica-ultimate-workbench
workbench-design-docs
Product design, technical design documents, user-facing copy, specs, diagrams, and handoff documentation.
7workbench-token-context-discipline
Compact context, cache-aware execution, scoped evidence reads, and role-specific skill attachment discipline.
6workbench-gsd-tasking
Owner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.
6workbench-memory-synthesis
Durable memory, session summaries, decision logs, issue closeout synthesis, and compact handoffs.
6workbench-implementation
Minimal-patch implementation, ops changes, scripts, automation specs, and local repository edits.
6workbench-research
Evidence-first research, architecture discovery, vendor documentation review, benchmark reading, and unknown-system analysis.
6