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
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 skills add NousResearch/hermes-agent --skill watchersgit clone --depth 1 https://github.com/NousResearch/hermes-agentWrote 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/watchers)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/watchers"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/watchers/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/watchers"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/watchers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Tool Misuse · line 99 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 76 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.
- medium Output Handling · line 108 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00017 | $0.01144 |
| Opus 5 | $0.00009 | $0.00572 |
| Sonnet 5 | $0.00003 | $0.00229 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
watchers 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 10d 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.
Copies of this mod
7 near-identical copies found in the catalogue:
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watchers
Poll external sources on an interval and react only to new items. Three ready-made scripts plus a shared watermark helper; wire them into a cron job (or run them ad-hoc from the terminal).
When to Use
- User wants to watch an RSS/Atom feed and be notified of new entries
- User wants to watch a GitHub repo's issues / pulls / releases / commits
- User wants to poll an arbitrary JSON endpoint and get notified on new items
- User asks for "a watcher for X" or "notify me when X changes"
Mental model
A watcher is just a script that:
- Fetches data from the external source
- Compares against a watermark file of previously-seen IDs
- Writes the new watermark back
- Prints new items to stdout (or nothing on no-change)
The scripts below handle all three. The agent runs them via the terminal tool — from a cron job, a webhook, or an interactive chat — and reports what's new.
Ready-made scripts
All three live in $HERMES_HOME/skills/devops/watchers/scripts/ once the skill is installed. Each reads WATCHER_STATE_DIR (defaults to $HERMES_HOME/watcher-state/) for its state file, keyed by the --name argument.
| Script | What it watches | Dedup key |
|---|---|---|
watch_rss.py |
RSS 2.0 or Atom feed URL | <guid> / <id> |
watch_http_json.py |
Any JSON endpoint returning a list of objects | Configurable id field |
watch_github.py |
GitHub issues / pulls / releases / commits for a repo | id / sha |
All three:
- First run records a baseline — never replays existing feed
- Watermark is a bounded ID set (max 500) to cap memory
- Output format:
## <title>\n<url>\n\n<optional body>per item - Empty stdout on no-new — the caller treats that as silent
- Non-zero exit on fetch errors
Usage
Run a watcher directly from the terminal tool:
python $HERMES_HOME/skills/devops/watchers/scripts/watch_rss.py \
--name hn --url https://news.ycombinator.com/rss --max 5
Watch a GitHub repo (set GITHUB_TOKEN in ${HERMES_HOME:-~/.hermes}/.env to avoid the 60 req/hr anonymous rate limit):
What ships with it
4 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.
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.
- 10d ago First seen · 113 lines · 17 tokens per session scan A 29c01df1882d
watchers is a skill published in the GitHub repository NousResearch/hermes-agent (243,598 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,144 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
rubyllm
Build and maintain Ruby or Rails applications with the RubyLLM AI framework. Use for chats, agents, tools, structured output, media generation, transcription, OCR, moderation, embeddings, reranking, Rails integration, and RubyLLM upgrades; not for contributing to the framework itself.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…
options
Present multiple design options as a vertical stack of anchored turns.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
pptx
Create and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.