Hermes Commands & Skill Commands

📖 Hermes Commands

/start -- Acknowledge platform start pings without a reply/new [name] -- Start a new session (fresh session ID + history) (alias: /reset)/topic [off|help|session-id] -- Enable or inspect Telegram DM topic sessions/save <json|md|html> [filename] [redact] -- Export the current conversation (bare /save shows usage)/retry -- Retry the last message (resend to agent)/undo [N] -- Back up N user turns and re-prompt (default 1)/title [name] -- Set a title for the current session/branch [--here] [name] -- Branch the current session (new thread on Discord/Telegram/Slack/Matrix; --here stays here) (alias: /fork)/compress [here [N] | focus topic | --preview|--dry-run] -- Compress conversation context (add 'here [N]' to keep recent N turns; --preview shows what would happen) (alias: /compact)/rollback [number] [--all] -- List or restore filesystem checkpoints (restores keep your hand-edits; --all overrides)/stop -- Kill all running background processes/pause [reason | off] -- Pause new work globally (emergency stop); '/pause off' resumes/approve [session|always] -- Approve a pending dangerous command/deny [all] [reason] -- Deny a pending dangerous command (optionally with a reason)/bg <prompt> -- Run a prompt in a separate background session/btw <question> -- Ask a side question about the current conversation without interrupting it/agents -- Show active agents and running tasks (alias: /tasks)/queue [<prompt>|list|edit N <prompt>|rm N|move A B|clear] -- Queue a prompt for the next turn, or list/edit/rm/move/clear queued prompts (alias: /q)/steer <prompt> -- Inject a message after the next tool call without interrupting/goal [text | draft <text> | show | gate add <cmd> | pause | resume | clear | status | wait <pid> | unwait] -- Set a standing goal Hermes works on across turns until achieved/heartbeat [every <interval> <prompt> | status | pause | resume | clear] -- Set a recurring prompt that re-enters this session when idle (alias: /hb)/refine [focus instructions] -- Review this conversation now and save lessons to memory/skills/review [review instructions] -- Spawn an independent subagent to review the work just discussed (PR, code, docs)/loop [interval] <prompt> [--times N] [--until <condition>] | status | pause | resume | stop -- Re-run a prompt on a recurring interval in this session (alias: /proactive)/plan [task] -- Write a markdown implementation plan to .hermes/plans/ without executing anything/moa <prompt> -- Run one prompt through the default Mixture of Agents preset, then restore your model/subgoal [text | remove N | clear] -- Add or manage extra criteria on the active goal/status -- Show session, model, token, and context info/egress [status] -- Show Docker egress proxy status/context [all] -- Show detailed context window view with usage gauge, category breakdown, compression stats, and throughput (alias: /ctx)/whoami -- Show your slash command access (admin / user)/profile -- Show active profile name and home directory/sethome -- Set this chat as the home channel (alias: /set-home)/resume [name] -- Resume a previously-named session/sessions -- Browse and resume previous sessions/model [model] [--provider name] [--reasoning level] [--global|--session] [--refresh] -- Switch model (session-scoped; --global to persist)/codex-runtime [auto|codex_app_server] -- Toggle codex app-server runtime for OpenAI/Codex models/personality [name] -- Set a predefined personality/diff [staged|all|session] [--stat] [path...] -- Show git changes in the working directory/footer [on|off|status] -- Toggle gateway runtime-metadata footer on final replies/yolo -- Toggle YOLO mode (skip all dangerous command approvals)/approvals [manual|smart|off] -- Show or set the persistent dangerous-command approval mode/reasoning [level|show|hide|full|clamp] [--global] -- Manage reasoning effort and display (1/3)
/fast [normal|fast|auto|cold|status] [--global] -- Fast mode — OpenAI Priority Processing / Anthropic Fast Mode (normal/fast/auto/cold)/voice [on|off|tts|status] -- Toggle voice mode/busy [queue|steer|interrupt|status] -- Control how messages behave while Hermes is working/memory [pending|approve|reject|approval] [id|on|off] -- Review pending memory writes / toggle the approval gate/bundles -- List skill bundles (aliases /<name> for multiple skills)/learn <what to learn from> -- Learn a reusable skill from anything you describe (dirs, URLs, this chat, notes)/init [notes] -- Generate or update AGENTS.md project instructions from a repo scan/suggestions [accept|dismiss N | catalog] -- Review suggested automations (accept/dismiss) (alias: /suggest)/blueprint [name] [slot=value ...] -- Set up an automation from a blueprint template (alias: /bp)/curator [subcommand] -- Background skill maintenance (status, run, pin, archive, list-archived)/kanban [subcommand] -- Multi-profile collaboration board (tasks, links, comments)/reload-mcp -- Reload MCP servers from config/reload-skills -- Re-scan ~/.hermes/skills/ for newly installed or removed skills/commands [page] -- Browse all commands and skills (paginated)/help [skills|<filter>] -- Show available commands (/help skills lists skill commands, /help <text> filters)/restart -- Gracefully restart the gateway after draining active runs/usage [reset [--force]] -- Show token usage and rate limits; reset redeems a banked Codex limit reset/login -- Sign in with a Nous account (keeps your connectors)/topup -- Show your Nous balance and manage billing on the portal/insights [days] -- Show usage insights and analytics/platform <pause|resume|list> [name] -- Pause, resume, or list a failing gateway platform/update -- Update Hermes Agent to the latest version/version -- Show Hermes Agent version (alias: /v)/debug [nous|local] -- Upload debug report (system info + logs) and get shareable links
⚡ Skill Commands (987 active):/9router — 9Router dashboard auth, password reset, and tunnel access./abusing-dpapi-for-credential-access — Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys) online or offline using SharpDPAPI, SharpChrome, Mimikatz, or Impacket's dpapi.py, including domain-wide decryption via the DPAPI backup key. Use during authorized red-team credential-access engagements after gaining a foothold or when triaging DPAPI blobs pulled from a host./abusing-shadow-credentials-for-privesc — Take over Active Directory accounts by writing attacker-controlled public keys to msDS-KeyCredentialLink (Shadow Credentials) with pyWhisker, Whisker, or Certipy, then authenticate via PKINIT to recover the target's NT hash without a password reset. Use when BloodHound shows GenericWrite/GenericAll/AddKeyCredentialLink over a target, as a stealthier alternative to ForceChangePassword, during authorized red-team engagements./achieving-cmmc-level-2-compliance — Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when an organization handles Controlled Unclassified Information (CUI) under a DoD contract, when a contract carries DFARS clause 252.204-7012/7019/7020/7021, when preparing for or responding to a CMMC assessment, when computing or improving an SPRS score, when building a System Security Plan or POA&M for 800-171, or when scoping which systems are in the CUI boundary. Keywords: CMMC, CMMC Level 2, NIST 800-171, SP 800-171 Rev 2, CUI, FCI, SPRS, DFARS 7012, C3PAO, POA&M, System Security Plan, DoD Assessment Methodology, 110 controls, defense industrial base, DIB, FedRAMP equivalency. (2/3)
/acquiring-disk-image-with-dd-and-dcfldd — Create forensically sound bit-for-bit disk images with dd or dcfldd on a Linux forensic workstation, preserving evidence integrity through hash verification (MD5/SHA) during acquisition. Use when imaging a suspect drive, USB device, or memory card for investigation, preserving volatile disk evidence during incident response, or producing a verified copy for legal or law-enforcement proceedings before any destructive analysis./agentic — Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows./airtable — Airtable REST API via curl. Records CRUD, filters, upserts./analyzing-active-directory-acl-abuse — Detect dangerous ACL misconfigurations in Active Directory using ldap3 to identify GenericAll, WriteDACL, and WriteOwner abuse paths/analyzing-android-malware-with-apktool — Perform static analysis of Android APK malware using apktool for resource decompilation, jadx for Java source recovery, and androguard for manifest inspection, dangerous permission-combination detection, and identification of obfuscated code, dynamic code loading, and reflection-based API calls. Use to statically triage a suspicious APK without executing it or to build mobile malware detection rules./analyzing-api-gateway-access-logs — Parses API Gateway access logs (AWS API Gateway, Kong, Nginx) to detect BOLA/IDOR attacks, rate limit bypass, credential scanning, and injection attempts. Uses pandas for statistical analysis of request patterns and anomaly detection. Use when investigating API abuse or building API-specific threat detection rules.

... and 977 more. Use /commands for the full paginated list. (3/3)