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/seenode/seenode-agent-plugin/troubleshootnpx skills add seenode/seenode-agent-plugin --skill troubleshootgit clone --depth 1 https://github.com/seenode/seenode-agent-pluginWhat 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 | $0.00075 | $0.01316 |
| Opus 5 | $0.00037 | $0.00658 |
| Sonnet 5 | $0.00015 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
troubleshoot 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshoot Seenode deployments
Identify the failing application, read deployment state and logs, classify the failure, fix via code and/or MCP settings, redeploy, and verify.
Prerequisites
get_current_team()
list_applications(application_type="web") # also try worker / private
If MCP auth fails, complete Seenode OAuth and retry.
Workflow
1. Identify the application
list_applications(application_type="web"|"worker"|"private")
get_application(application_id=...)
get_build_settings(application_id=...)
Confirm name, type, git repo/branch, and current build settings before changing anything.
2. Check deployment state
get_deployments(application_id=...)
Prefer waiting instead of busy-polling:
wait_for_deployment(application_id=..., deployment_uuid=null, timeout_seconds=300)
To abort a stuck in-progress build:
cancel_deployment(application_id=..., deployment_uuid=...)
Use liveDeployment and lastDeployment plus state:
| State | Meaning |
|---|---|
NEW / RUNNING |
Still in progress — wait_for_deployment |
SUCCESSFUL |
Build/release OK; look at runtime/request logs if the app still misbehaves |
FAILED |
Read build then runtime logs |
CANCELLED |
Ask whether to redeploy |
LIMITS |
Team/plan limits — get_team_limits / billing skill |
3. Pull logs
get_application_logs(application_id=..., log_types=["build"], limit=100)
get_application_logs(application_id=..., log_types=["runtime"], limit=100)
get_application_logs(application_id=..., log_types=["request"], limit=50) # if HTTP errors
Optional: search for a known string; mode="history" + range_preset for older windows.
4. Classify the failure
Match against references/error-patterns.md. Common classes:
- Missing / wrong env vars
- Port binding (
127.0.0.1only, wrong port) - Build command / dependency failures
- Database connection (re-link, do not paste passwords)
- OOM / high memory (metrics)
- Wrong runtime image
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 159 lines · 75 tokens per session scan A b03f259a4217
troubleshoot is a skill published in the GitHub repository seenode/seenode-agent-plugin (2 stars, last pushed 23d ago), licensed MIT. It adds 75 tokens to every session and 1,316 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.