agentleFS
Sign inStart free
michaelandrewgamblemichaelandrewgamble/workflows-conductor/skills/status/SKILL.md

status

Skill1 starsChanged 4 months agoMITView on GitHub

List Claude Code dynamic workflow runs (status, agents, tokens, duration) by reading run records from ~/.claude/projects. Use when the user asks about workflow runs, ultracode runs, run status, or anything /workflows would show.

177 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use off, list and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • StakeholderSenseiSkill

    off

    Disable polygraph for this repo (user-only escape hatch; all hooks no-op)

    Also in 4 projects that use this

  • SuShuhengSkill

    list

    Use when checking obshare-cli upload history, finding document tokens, or reviewing previous upload URLs and permission snapshots.

    Also in 8 projects that use this

  • kennethleungtySkill

    pause

    Pause — stop the music (alias for /stop)

    Also in 6 projects that use this

  • codebycoreySkill

    new

    Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.

    Also in 7 projects that use this

  • michaelenglandSkill

    import

    This skill should be used when the user wants to import an existing .pptx file into deckwright, bring in a PowerPoint that was created outside this tool, reverse-engineer a presentation for editing, or invoke /deckwright:import. Converts a .pptx into a PptxGenJS generation script so it can be edited and regenerated through the deckwright pipeline.

    Also in 5 projects that use this

  • genomewalkerSkill

    resume

    Resume a thread by loading its ~800-token context capsule

    Also in 15 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 146 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Only ever consume the reader's JSON output — NEVER read wf_*.json run records directly (they embed 30–70 KB workflow scripts).

    line 13
  2. Distinctive:

    If the user names a run ID, drill down with the other conductor tools:

    line 21

“Common” is measured: kept by at least 6 in 10 of the 146 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/conductor:status — list and inspect dynamic workflow runs

Backed by the plugin's conductor MCP server (reader library underneath). Requires Node ≥ 18 on PATH.

Context-cost rules (mandatory)

  • Only ever consume the reader's JSON output — NEVER read wf_*.json run records directly (they embed 30–70 KB workflow scripts).
  • Agent transcripts are returned as file paths; Read one only if the user asks about a specific agent, and only with a line limit.
  • Render at most the requested row limit; state how many were omitted.

Procedure

  1. List runs with the conductor MCP server's list_runs tool: {cwd: <absolute project path>, scope: "project" | "all", limit: 10}. Default scope is the current project; --all in the user's arguments means scope "all".
  2. If the user names a run ID, drill down with the other conductor tools:
    • get_run {runId} — metadata + result preview (never contains the script)
    • get_agents {runId} — per-agent state and transcript file paths
    • get_script {runId} — full script source (large; only on explicit request)

Fallback: if the conductor MCP tools are unavailable in this session (server not loaded), use the identical CLI:

node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" list --cwd "$PWD" [--all] [--limit N]
node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" <get|agents|script> <runId>
  1. Render a markdown table from runs: Run ID · Name · Status · Agents · Tokens · Duration · When · Expires. Interpretation rules:
    • status is a raw passthrough. If statusRecognized is false, render the value verbatim with an "(unrecognized status)" marker — do not guess what it means.
    • compat of degraded/unknown-format/unreadable → append a warning marker to that row and mention that its record was written in an unexpected format (possibly a newer CLI).
    • liveCandidates rows have no run record yet: render them in a separate short section as live? (recent activity) or stale (interrupted?), with lastActivity. Note once that live-state is heuristic until the CLI writes the terminal record.
    • expiresInDays ≤ 5 → mark the row "expires soon" (sessions auto-delete after ~30 days).
  2. Close with one line of totals from totalRuns / projectCount / omitted. If runs is empty and there are no live candidates: say no workflow runs were found and note that dynamic workflows require Claude Code CLI ≥ 2.1.154 (launch one with an ultracode: prompt).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free