fr-runner

fr-runner is a skill for Claude Code from derio-net/super-fr. It costs 83 tokens per session (607 once invoked), scanned A, original, MIT.

A skill for operating and troubleshooting an autonomous runner, including the VibeKanban adapter. The runner picks up queued work phases and sends them to coding workspaces.

In plain words
What is it for?
Use it to check runner health, inspect phase readiness, diagnose dispatch failures, verify repository registration, and recover orphaned workspaces.
Why use it?
It helps explain why queued work was not dispatched, whether the runner is healthy, and how to recover workspaces left behind after a problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the super-fr-dispatch plugin — 2 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/derio-net/super-fr/fr-runner
Any agent
npx skills add derio-net/super-fr --skill fr-runner
Clone the repo
git clone --depth 1 https://github.com/derio-net/super-fr

Made for: Claude Code.

Or install super-fr-dispatch, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fr-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/derio-net/super-fr/fr-runner.svg)](https://agentmods.dev/skills/derio-net/super-fr/fr-runner)
Your own site
<a href="https://agentmods.dev/skills/derio-net/super-fr/fr-runner"><img src="https://agentmods.dev/badge/skills/derio-net/super-fr/fr-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 607 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.00607
Opus 5 $0.00042 $0.00303
Sonnet 5 $0.00017 $0.00121
Haiku 4.5 $0.00008 $0.00061

Measured 5d ago against content hash c61c2b132600, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fr-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/super-fr-dispatch/skills/fr-runner/SKILL.md · 54 lines

What it actually says

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.
  2. Is a phase eligible? fr status <plan-dir> 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).
  3. 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 <plan-dir> --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.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 54 lines · 83 tokens per session scan A c61c2b132600

Subscribe to this mod's changes

fr-runner is a skill published in the GitHub repository derio-net/super-fr (1 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 607 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

release-it

Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…

wondelai/skills · 131 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

git-investigate

Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.

sd0xdev/sd0x-harness · 53 tokens

analyze

Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…

rsmdt/the-startup · 118 tokens

simplify

Wrap-up refactoring — simplify code, eliminate duplication, preserve behavior.

sd0xdev/sd0x-harness · 16 tokens

incremental-analysis

Detect existing workspace, diff current sources against high water mark metadata, classify specs as unchanged/stale/orphaned/new, re-analyze only what changed. Activates automatically when /analyze finds an existing workspace.

prime-radiant-inc/greenfield · 47 tokens