Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NousResearch/hermes-agentnpx agentmods add skills/nousresearch/hermes-agent/comfyuiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nousresearch/hermes-agent/comfyui)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/comfyui"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/comfyui/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/comfyui"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/comfyui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 8 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 377 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 378 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 605 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 379 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Data Exfiltration · line 540 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- low Supply Chain · line 406 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
What 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 5.1 | $0.00015 | $0.06283 |
| Opus 5.5 | $0.00006 | $0.02513 |
| Sonnet 5.5 | $0.00003 | $0.01257 |
| Haiku 4.5 | $0.00002 | $0.00628 |
Grade D, and why
comfyui scanned grade D with 3 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 1mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST http://127.0.0.1:8188/queue -d '{"clear": true}' # cancel pending Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://127.0.0.1:8188/queue | python -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8188/system_stats 2>/dev/null && echo "server: running" Copies of this mod
8 near-identical copies found in the catalogue:
- comfyui — 100% identical, 0 lines differ
- comfyui — 100% identical, 0 lines differ
- comfyui — 98% identical, 48 lines differ
- comfyui — 98% identical, 48 lines differ
- comfyui — 98% identical, 52 lines differ
- comfyui — 98% identical, 50 lines differ
- comfyui — 98% identical, 48 lines differ
- comfyui — 98% identical, 46 lines differ
How it starts
The opening of the file, as written. The whole thing — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI
Generate images, video, audio, and 3D content through ComfyUI using the
official comfy-cli for setup/lifecycle and direct REST/WebSocket API
for workflow execution.
What's in this skill
Reference docs (references/):
official-cli.md— everycomfy ...command, with flagsrest-api.md— REST + WebSocket endpoints (local + cloud), payload schemasworkflow-format.md— API-format JSON, common node types, param mappingtemplate-integrity.md— convertingcomfyui-workflow-templatesfrom editor format to API format: Reroute bypass, dotted dynamic-input keys (values.a,resize_type.width), Cloud quirks (302 redirect, 1 concurrent free-tier job, 1080p VRAM ceiling), Discord-compatible ffmpeg stitch. Authored by @purzbeats. Load this whenever you're starting from an official template.
Scripts (scripts/):
| Script | Purpose |
|---|---|
_common.py |
Shared HTTP, cloud routing, node catalogs (don't run directly) |
hardware_check.py |
Probe GPU/VRAM/disk → recommend local vs Comfy Cloud |
comfyui_setup.sh |
Hardware check + comfy-cli + ComfyUI install + launch + verify |
extract_schema.py |
Read a workflow → list controllable params + model deps |
check_deps.py |
Check workflow against running server → list missing nodes/models |
auto_fix_deps.py |
Run check_deps then comfy node install / comfy model download |
run_workflow.py |
Inject params, submit, monitor, download outputs (HTTP or WS) |
run_batch.py |
Submit a workflow N times with sweeps, parallel up to your tier |
ws_monitor.py |
Real-time WebSocket viewer for executing jobs (live progress) |
health_check.py |
Verification checklist runner — comfy-cli + server + models + smoke test |
fetch_logs.py |
Pull traceback / status messages for a given prompt_id |
Example workflows (workflows/): SD 1.5, SDXL, Flux Dev, SDXL img2img,
SDXL inpaint, ESRGAN upscale, AnimateDiff video, Wan T2V. See
workflows/README.md.
What ships with it
32 files 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.
- references/official-cli.md 7.4 KB
- references/rest-api.md 10 KB
- references/template-integrity.md 8.6 KB
- references/workflow-format.md 7.8 KB
- scripts/_common.py 33 KB runs code
- scripts/auto_fix_deps.py 8.3 KB runs code
- scripts/check_deps.py 17 KB runs code
- scripts/comfyui_setup.sh 10 KB runs code
- scripts/extract_schema.py 11 KB runs code
- scripts/fetch_logs.py 5.5 KB runs code
- scripts/hardware_check.py 18 KB runs code
- scripts/health_check.py 8.0 KB runs code
- scripts/run_batch.py 8.8 KB runs code
- scripts/run_workflow.py 31 KB runs code
- scripts/ws_monitor.py 10 KB runs code
- tests/conftest.py 1.5 KB runs code
- tests/pytest.ini 132 B
- tests/README.md 2.2 KB
- tests/test_check_deps.py 2.3 KB runs code
- tests/test_cloud_integration.py 4.2 KB runs code
- tests/test_common.py 16 KB runs code
- tests/test_extract_schema.py 7.7 KB runs code
- tests/test_run_workflow.py 8.6 KB runs code
- workflows/animatediff_video.json 2.0 KB
- workflows/flux_dev_txt2img.json 2.2 KB
- workflows/README.md 3.8 KB
- workflows/sd15_txt2img.json 1.4 KB
- workflows/sdxl_img2img.json 1.6 KB
- workflows/sdxl_inpaint.json 1.8 KB
- workflows/sdxl_txt2img.json 1.4 KB
- workflows/upscale_4x.json 864 B
- workflows/wan_video_t2v.json 2.1 KB
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.
- 1mo ago First seen · 613 lines · 15 tokens per session scan D 1013a06bf6ac
comfyui is a skill published in the GitHub repository NousResearch/hermes-agent (256,867 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 6,283 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 3 findings (sends data to an external url, downloads and executes remote code, 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
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from…
options
Present multiple design options as a vertical stack of anchored turns.
notion
Search, read, create, and update Notion pages via the Notion MCP.
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.