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.
npx agentmods add skills/imran31415/kube-coder/remote-tasknpx skills add imran31415/kube-coder --skill remote-taskgit clone --depth 1 https://github.com/imran31415/kube-coderWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00040 | $0.01572 |
| Opus 5 | $0.00020 | $0.00786 |
| Sonnet 5 | $0.00008 | $0.00314 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
remote-task scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://localhost:6080/api/claude/tasks" \ How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote Task Skill
Launch Claude tasks on remote kube-coder workspace pods, check their status, or view output.
Prerequisites
This skill requires:
kubectlaccess to the cluster- A running workspace pod (deployed via
make deploy-<user>) - An API token generated on the pod
How It Works
The workspace pod runs a Python HTTP server on port 6080 that exposes a Claude Task API. Tasks launch as interactive tmux sessions running claude — users can attach to approve permissions and provide input.
Commands
Based on $ARGUMENTS, perform ONE of the following:
1. If $ARGUMENTS is "status" — List all tasks
# Port-forward if needed
kubectl port-forward -n coder svc/ws-imran 6080:6080 &
PF_PID=$!
sleep 2
TOKEN=$(kubectl exec -n coder $(kubectl get pods -n coder -l app=ws-imran -o jsonpath='{.items[0].metadata.name}') -c ide -- cat /home/dev/.claude-tasks/.api-token 2>/dev/null)
curl -s "http://localhost:6080/api/claude/tasks" \
-H "Authorization: Bearer $TOKEN" | python3 -m json.tool
kill $PF_PID 2>/dev/null
Display the results as a formatted table showing: task_id, status, prompt (truncated), and created_at (as relative time).
2. If $ARGUMENTS starts with "attach" — Show how to attach to a task
Extract the task ID from the arguments. Then tell the user:
- Open the dashboard at the workspace URL and click "Attach" on the task
- Or run:
kubectl exec -it -n coder <pod> -c ide -- tmux attach-session -t claude-<task_id>
Also show recent output:
kubectl exec -n coder <pod> -c ide -- tmux capture-pane -t claude-<TASK_ID> -p -S -30
3. If $ARGUMENTS starts with "output" — Show task output
Extract the task ID from the arguments. Run:
kubectl exec -n coder <pod> -c ide -- tmux capture-pane -t claude-<TASK_ID> -p -S -50
4. If $ARGUMENTS starts with "kill" — Kill a task
Extract the task ID from the arguments. Run:
kubectl port-forward -n coder svc/ws-imran 6080:6080 &
PF_PID=$!
sleep 2
TOKEN=$(kubectl exec -n coder $(kubectl get pods -n coder -l app=ws-imran -o jsonpath='{.items[0].metadata.name}') -c ide -- cat /home/dev/.claude-tasks/.api-token 2>/dev/null)
curl -s -X DELETE "http://localhost:6080/api/claude/tasks/<TASK_ID>" \
-H "Authorization: Bearer $TOKEN" | python3 -m json.tool
kill $PF_PID 2>/dev/null
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.
- 3d ago First seen · 146 lines · 40 tokens per session scan A a421c8ea0781
remote-task is a skill published in the GitHub repository imran31415/kube-coder (349 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 1,572 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…