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/sandyup/comfyui-mcp/report-bugnpx skills add sandyup/comfyui-mcp --skill report-buggit clone --depth 1 https://github.com/sandyup/comfyui-mcpWhat 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 | $0.00135 | $0.01898 |
| Opus 5 | $0.00068 | $0.00949 |
| Sonnet 5 | $0.00027 | $0.00380 |
| Haiku 4.5 | $0.00014 | $0.00190 |
Grade A, and why
report-bug scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS -X POST "$WORKER_URL" \ How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-heal & report bugs (make the ecosystem better)
Goal: when something is broken, don't just stop — diagnose it, try to fix it so the user keeps working, and get the fix/report to whoever can fix it upstream. Do this autonomously: act, then inform the user with a short summary — don't pepper them with permission prompts. (Exceptions where you DO pause: a fix that touches the user's own workflow/data, anything large/risky, or anything you can't make safe — explain and ask.)
This is for bugs in software, not ordinary workflow/generation errors (OOM,
missing model, bad params → use troubleshooting). First decide whose bug it is.
Step 1 — Diagnose (root cause, not symptom)
- Read the exact error + stack. For ComfyUI runs:
get_history,get_logs. - Follow the stack to the actual file/line. Read the code there.
- Form a concrete root cause + a minimal fix you can defend.
Step 2 — Classify whose bug it is
- OURS —
comfyui-mcp(server/tools/orchestrator/agent) orcomfyui-mcp-panel(the sidebar pack / panel JS /__init__.py). → Steps 3–5 (self-heal + Worker/PR). - THIRD-PARTY — a custom node pack, or ComfyUI core itself. → Step 6 (their GitHub; our Worker can't file there).
Step 3 — Attempt a local fix (so the user keeps working)
Patch the code where it actually runs so relief is immediate:
comfyui-mcp: find the running install from the stack path. If a source checkout exists, fix the.tssource andnpm run build; if only the built package is present, patch thedist/*.jsdirectly. Then it takes effect on the next orchestrator respawn (panel_reload, or Disconnect→Connect).comfyui-mcp-panel: patch the file under the pack (web/js/…for UI,__init__.pyfor the pack) — UI changes need a hard-refresh.
Keep the patch minimal and reversible. It's fine that a future update will overwrite it — that's expected; the user runs the patched version in the meantime. If you genuinely can't fix it locally (the bug is upstream-only — in the SDK, ComfyUI, or needs a release), say so and skip to reporting, marked upstream-only.
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 · 136 lines · 0 tokens per session scan A 565d86840f31
report-bug is a skill published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 1,898 once invoked, about $0.0007 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 2026-08-31.
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.
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…