AgentStack
SKILL verified MIT Self-run

Fr Runner

skill-derio-net-super-fr-fr-runner · by derio-net

>

No reviews yet
0 installs
1 views
0.0% view→install

Install

$ agentstack add skill-derio-net-super-fr-fr-runner

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Fr Runner? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

fr-runner

The runner is the autonomous consumer of queued phases. The framework surface is fr_dispatch (discover_plans + tick against the Runner protocol); the VibeKanban adapter is fr_vk (VkRunner, MCP client, card/workspace creation, the cron daemon python -m fr_vk.bridge). Neither is wired into the fr CLI — the daemon consumes them as a library on its pod.

Health checks

  1. Is the daemon ticking? The heartbeat gauge

(willikins_heartbeat_last_success_timestamp) must be recent. Sync/failure counters: willikins_vk_bridge_sync_total, willikins_vk_bridge_failure_total{reason=…} — reasons: project_id_missing, unknown_repo, mcp_error, gh_error.

  1. Is a phase eligible? fr status on the plan: a phase

dispatches only when its RENDERED labels say ready-but-not-synced, it has a tracking_issue, and the plan + spec are on origin/HEAD (the bridge pod pulls; reachability is why dispatch requires merged plans).

  1. Repo known to the runner? The VK adapter refuses repos its board

doesn't list (unknown_repo failures) — add the repo in VK first.

Common faults

  • Queued forever, no failures: pod checkout stale (pull the repo on

the pod), or every slot is in use (workspace budget — the runner defers and retries next tick, no action needed).

  • project_id_missing: the pod env lost VK_DERIO_OPS_PROJECT_ID.
  • Dispatched in error: fr undispatch --yes closes the

Issues and nulls the tracking fields; the runner's reaper archives the orphan workspaces on its next pass.

  • Card exists, workspace missing: set

VK_BRIDGE_RECOVER_ORPHAN_CARDS=1 for one tick (opt-in recovery).

Boundaries

This skill OPERATES runners; queueing work to them is fr-dispatch's ceremony, and implementing phases is fr-execute's. The daemon never creates Issues (operator-only via fr apply --yes) and never implements work itself.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.