hermes-agent
Skill0 starsChanged 6 days agoMITView on GitHub
Use, configure, theme, extend, and orchestrate Hermes Agent — including multi-bot Telegram multiplex gateways and gateway persistence. Observed user phrasing: 'spawn sub agent / subagents to make all FRD becoming real', 'we need to spawn sub agent', 'can Hermes do X' / 'how do I set up X in Hermes', 'only spawn hermes', 'hanya spawn hermes', 'hermes' with a task to delegate.
- Reads credentials
23 other projects use a version of this, 7 of them edited.
Adopted by
Most recently taken up by
- ashleysbrain/skillstheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
- andrewalhaj/custom-hermesagenttheir own version, first seen Oct 20, 2026
- juanmackie/juanskillstheir own version, first seen Oct 20, 2026
- Fahrnetic/engineering-agent-skill-workflowtheir own version, first seen Oct 15, 2026
- AtlasOmnia/hermes-custom-packtheir own version, first seen Oct 13, 2026
Used with
Projects with it also use sdlc-review, teams-meeting-pipeline and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
aivrarSkillsdlc-review
Review Kanban handoffs and route verified outcomes.
Also in 5 projects that use this
john-data-chenSkillteams-meeting-pipeline
Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.
Also in 6 projects that use this
aivrarSkillsession-librarian
Organize sessions by prompt: find, rename, archive, prune.
Also in 3 projects that use this
john-data-chenSkilltouchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
Also in 4 projects that use this
yusei531642Skillclaude-design
Vibe-Editor の UI を「Claude.ai + Claude Code 公式風」にリファインする際に参照するデザインガイド。色 (warm off-white / terra cotta #d97757)、タイポ (Claude 返答は serif・ユーザーは sans)、余白、記号 (⏺・⎿・スピナー)、アニメ (150ms / cubic-bezier(.4,0,.2,1))、メッセージングトーンの具体値を提供する。UI 刷新・新規コンポーネント作成・テーマ追加・エージェント発話の装飾など、見た目やトーンの判断が必要な作業で必ず参照。
Also in 8 projects that use this
tunnckoCoreSkillnode-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol CLI.
Also in 6 projects that use this
- +3 more from aivrar
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 7
- NousResearch/hermes-agent★ 262k23% same
- aivrar/portable-hermes-agent★ 23928% same
- Samin12/skills★ 825% same
- 2867203296/hermes-agent★ 025% same
- barzzly/BarzzLyp_Agent_Skills★ 026% same
- Gopyr/gopyr-skills-hub★ 015% same
- nobodyohm-web/Thot★ 028% same
Wrote their own version · 16
- fathah/hermes-desktop★ 14ksame name
- Tommy-yw/RunbookHermes★ 546same name
- RedWoodOG/Hermes-Desktop★ 177same name
- AtlasOmnia/donna-starter★ 136same name
- AtlasOmnia/hermes-custom-pack★ 75same name
- delorenj/skills★ 17same name
- Fahrnetic/engineering-agent-skill-workflow★ 2same name
- john-data-chen/hermes-agent-backup★ 2same name
- ashleysbrain/skills★ 1same name
- juanmackie/juanskills★ 1same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/skill-authoring/tools/AGENTS.mdAGENTS.md
- aes-docsSkill
- aes-fixSkill
- aes-layerSkill
- aes-migrationSkill
- android-emulator-linux-gpsSkill
- computer-useSkill
- flatpak-chromium-automationSkill
- qwen-webSkill
- grok-buildSkill
- omnirouteSkill
- orcaSkill
- account-managerSkill
- brave-setupSkill
- password-managerSkill
- codegraphSkill
- deep-cleanSkill
- dogfoodSkill
- reviewSkill
- systematic-debuggingSkill
- blender-arwakySkill
- comfyuiSkill
- llm-writingSkill
- vision-arwakySkill
- playwright-toolingSkill
- setup-ci-quality-gatesSkill
- statuslineSkill
- systemd-headless-serviceSkill
- xdg-spec-complianceSkill
- figcraft-builderSkill
- figcraft-iconsSkill
- figcraft-motionSkill
- figcraft-prototyperSkill
- figcraft-reviewSkill
- figcraftSkill
- figcraft-svgSkill
- figcraft-typographySkill
- github-authSkill
- issue-makerSkill
- issue-workerSkill
- mergifySkill
- pr-babysitSkill
- releasingSkill
- repo-managerSkill
- ascii-artSkill
- ascii-videoSkill
- gif-searchSkill
- media-acquisitionSkill
- docxSkill
- emailSkill
- google-workspaceSkill
- notionSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- competitor-news-monitorSkill
- product-price-monitorSkill
- weekly-review-planningSkill
- arxivSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
Spawning instances: run additional Hermes processes as fully independent subprocesses — separate sessions, tools, and environments — never …
“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Hermes Agent
Hermes Agent is an open-source AI agent framework by Nous Research that runs in your terminal, a native desktop app, messaging platforms, and IDEs. It works with any LLM provider and runs on Linux, macOS, Windows, and WSL — self-improving through skills, persistent memory across sessions, a multi-platform gateway, and many surfaces driven by one agent core.
This skill is a hub. Load references/hub.md for orientation (scope rule, quick start, key paths, surfaces). Everything task-specific lives in the reference the Routing table names — load it before answering; do not answer detail questions from the body alone.
Global rules
- Never break prompt caching — don't change past context, toolsets, or the system prompt mid-conversation. The only exception is context compression.
- Message role alternation — never two assistant or two user messages in a row; only
toolresults can repeat. - No unnecessary clarifying questions. When the user's request is specific enough to act on, execute it. Only ask for clarification when the request is genuinely ambiguous and acting would change behavior in a way the user did not authorize. A path + flag is a directive, not a conversation opener.
- Secrets in
.env, settings inconfig.yaml— never tell a user to put a non-credential setting in.env. - Profile-safe paths —
get_hermes_home()in code,$HERMES_HOMEwhen resolving paths in a session. - Never hand-edit
config.yamlfor the user — usehermes config set KEY VAL; a stray indent can corrupt the file and break the live gateway. List-valued keys are still CLI work, but only when the value is passed as a JSON array literal (hermes config set skills.disabled '["a","b"]'); the comma form stores a scalar that every later read treats as one bogus name, so it silently does nothing. Verify withconfig get <key> --json, which must print an array. The single sanctioned non-CLI writer is the ruamel round-trip, used when the file carries comments the CLI rewrite would destroy. - Never stop the gateway from inside the gateway process.
systemctl --user stop hermes-gateway(or any SIGTERM to the gateway) is blocked: the kill signal propagates to this very process's children, so the command dies before it completes. Restart the gateway withhermes gateway restartfrom a separate shell outside the running gateway. Desktop-app restarts follow the same rule — kill the desktop process, not the gateway. - Two theming rules that hold even without loading the reference: apply skins yourself (
hermes config set display.skin <name>— every surface repaints live within ~a second; don't tell the user to run/skin), and to tweak one color, edit the ACTIVE skin (hermes skin set <key> <hex>) — never forkdefault, which drops the palette and resets the background. - Spawning instances: run additional Hermes processes as fully independent subprocesses — separate sessions, tools, and environments — never as in-process subagents.
Routing
| User wants... | Load |
| Orientation: scope rule, quick start, key paths, surfaces | references/hub.md |
| Anything not listed below — "can Hermes do X?", "how do I set up X?" | https://hermes-agent.nousresearch.com/docs/llms.txt |
| Bots that chat, run routines, or message each other; the Bots tab | docs: /user-guide/bot-mode |
| CLI commands, subcommands, flags, "how do I run X" | references/cli-reference.md |
| In-session slash commands | references/slash-commands.md |
| Provider setup, API keys, OAuth | references/providers-and-models.md |
| config.yaml sections, toolsets, voice/STT/TTS | references/configuration.md |
| AGENTS.md / .hermes.md / CLAUDE.md project rules | references/project-context-files.md |
| Standing behavior, identity, or task routing that must hold in every session | references/soul-md-routing.md |
| Secret redaction, PII, approval modes, "reset permissions" | references/security-privacy.md |
| Delegation, cron, curator, kanban | references/background-systems.md |
MCP servers (add, catalog, hermes mcp) | references/native-mcp.md |
| Webhook routes and event-driven runs | references/webhooks.md |
| A custom theme/skin ("synthwave theme", "change the gold ●") | references/themes.md + templates/skin.yaml |
| A desktop app UI element (pane, widget, ⌘K command, page) | references/desktop-plugins.md + templates/plugin.js |
| Desktop window looks transparent/see-through/"faded", or a window-translucency change won't stick after relaunch | references/desktop-translucency.md |
| A live TUI panel or modal widget (ticker, clock, dashboard) | references/tui-widgets.md + templates/clock.mjs |
| Pet mascots — install, select, scale, diagnose | references/petdex.md |
| Windows-specific issues (keybinds, WinError 10106, BOM) | references/windows-quirks.md |
| Debugging: voice, tools missing, gateway, aux models | references/troubleshooting.md |
| Contributing code: adding tools, slash commands, tests | references/contributor-guide.md |
| delegate_task "capped at N" reports | references/delegate-task-concurrency-diagnosis.md |
| "What sessions do I have about X?" / "Clean up my session library" / "archive the stale ones" | references/session-librarian.md |
| "Can app X use my Nous Portal subscription/OAuth?" | references/portal-auth-for-third-party-apps.md |
| Connecting a messaging platform (Telegram, Discord, Slack, WhatsApp, …) | docs: /user-guide/messaging |
| Multi-bot Telegram setup, multiplex profiles, "gateway always on", gateway bot not answering | references/multi-bot-telegram-run.md + references/systemd-always-on.md |
| Spawning additional Hermes instances or sub agents: one-shot, tmux PTY, multi-agent coordination, session resume | references/spawning.md |
| Why a newly added profile's bot stays silent / per-profile gateway unit exits 78 | references/multiplex-late-profile-adoption.md |
| Multiplex gateway code paths, token/secret scoping, auth sharing (source-verified) | references/multiplex-internals.md |
The reference list above is not the feature list — it is the set of topics that
need more than their docs page. For everything else Hermes ships, fetch
llms.txt and it maps the question to the page that answers it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

