gastown-sling
Skill1 starsChanged 50 days agoMITView on GitHub
Use when dispatching tasks to gastown polecats — submitting beads, checking status, choosing runtimes, or understanding the coordinator-worker architecture.
- Sends data out
In this repository113 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ac-ideateSkill
- ac-listSkill
- ac-roadmapSkill
- agentbridge-mcpSkill
- almanacSkill
- almquist-shellSkill
- ansible-fleetSkill
- apfsSkill
- apple-siliconSkill
- arena-actorsSkill
- asustor-nasSkill
- a-teamSkill
- atem-miniSkill
- at-tuiSkill
- autoresearchSkill
- babysitSkill
- bonzibuddySkill
- bop-brainstormSkill
- bop-catalogSkill
- bop-onSkill
- bop-teamSkill
- bop-workflowSkill
- bsd-portabilitySkill
- code-refactoringSkill
- codex-personasSkill
- context-graphSkill
- councilSkill
- datadog-backupSkill
- dd-tagsSkill
- delegateSkill
- deming-pdsaSkill
- deterministic-replaySkill
- dispatch-nuSkill
- durable-commitSkill
- elixir-gastown-opsSkill
- ergo-ircSkill
- esp32-tang-bridgeSkill
- fleet-evalSkill
- fleet-ircSkill
- freebsd-build-vmSkill
- freebsd-piSkill
- freebsdSkill
- ganttSkill
- gastown-opsSkill
- gh-authSkill
- gitea-releaseSkill
- gitea-runnerSkill
- henshuSkill
- irclaw-cluster-opsSkill
- irclaw-research-teamSkill
- irc-taskSkill
- jail-factorySkill
- jjSkill
- jobcard-systemSkill
- kubernetesSkill
- leptosSkill
- loreSkill
- lower-bound-reviewSkill
- macvlan-netSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 41
Default: claude (or stub if baseline mode off).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Gastown Sling — Dispatching Tasks to Polecats
Architecture
Polecats run on the coordinator (i9-zfs-pop:4000), not on Pi workers.
Pi workers with GASTOWN_ROLE=polecat_worker are BEAM federation nodes that suppress coordinator-only services (rate limiter). They don't receive polecats.
active polecats in /api/health = tasks currently running on coordinator. 0 = idle (normal).
Sling API
# Submit and immediately dispatch
curl -s -X POST http://10.0.2.230:4000/api/sling \
-H 'Content-Type: application/json' \
-d '{"description": "task prompt here", "runtime": "claude"}'
# → {"ok":true, "bead_id":"gt-xxxxx", "runtime":"claude"}
# Check bead status
curl -s http://10.0.2.230:4000/api/sling/gt-xxxxx
# List all beads
curl -s -H 'Authorization: Bearer $GASTOWN_API_TOKEN' http://10.0.2.230:4000/api/beadsAvailable Runtimes
| Runtime | What it runs | Notes |
claude | claude -p <prompt> | Claude Code CLI, non-interactive |
codex | codex exec --full-auto | Codex CLI, sandboxed |
ollama | ollama run qwen3-coder:480b-cloud | Local Ollama HTTP |
ollama_kimi | kimi-k2.5:cloud at 10.0.2.42 | pop4090 Ollama |
stub | echo | Testing only, instant |
Default: claude (or stub if baseline mode off).
Writing Good Bead Descriptions
The description is the full prompt sent to the runtime. Be specific:
# Good — self-contained, actionable
curl -X POST http://10.0.2.230:4000/api/sling \
-H 'Content-Type: application/json' \
-d '{
"description": "Clone all public repos from github.com/ryanmaclean to Gitea at http://10.0.2.230:3001. Use the Gitea API at /api/v1/repos/migrate. Token in GITEA_TOKEN env var. Work in /tmp/sync-$(date +%s). Log progress. When done, list all synced repos.",
"runtime": "claude"
}'Mix Task (local only)
# On i9, inside elixir-gastown dir
mix gastown.sling BEAD_ID --runtime claudeBead States
open → in_progress → done | failed | abandoned
Common Mistakes
| Mistake | Fix |
| Expecting Pi workers to run polecats | Polecats run on coordinator only |
| "0 polecats" = broken | 0 = idle, submit a bead to see count go up |
| Short descriptions | The description IS the prompt — be detailed |
| Wrong Ollama host for kimi | Use ollama_kimi runtime, not ollama |
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
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.

