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 claude-codegit 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/claude-code)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/claude-code"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/claude-code/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/claude-code"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 16 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 Excessive Agency · line 177 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 186 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Agent Snooping · line 342 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 588 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Tool Misuse · line 350 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.
- high Memory Poisoning · line 369 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Rogue Agent · line 255 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 277 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 326 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 385 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 405 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 419 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Rogue Agent · line 504 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 643 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 646 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 649 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00016 | $0.09164 |
| Opus 5.5 | $0.00006 | $0.03666 |
| Sonnet 5.5 | $0.00003 | $0.01833 |
| Haiku 4.5 | $0.00002 | $0.00916 |
Grade D, and why
claude-code scanned grade D with 2 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 17d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. **User:** `~/.claude/settings.json` (global) Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"deny": ["Read(.env)", "Bash(rm -rf *)"] Copies of this mod
8 near-identical copies found in the catalogue:
- claude-code — 100% identical, 47 lines differ
- claude-code — 100% identical, 49 lines differ
- claude-code — 100% identical, 47 lines differ
- claude-code — 97% identical, 59 lines differ
- claude-code — 95% identical, 58 lines differ
- claude-code — 95% identical, 58 lines differ
- claude-code — 94% identical, 55 lines differ
- claude-code — 94% identical, 60 lines differ
How it starts
The opening of the file, as written. The whole thing — 755 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code — Hermes Orchestration Guide
Delegate coding tasks to Claude Code (Anthropic's autonomous coding agent CLI) via the Hermes terminal. Claude Code v2.x can read files, write code, run shell commands, spawn subagents, and manage git workflows autonomously.
Prerequisites
- Install:
npm install -g @anthropic-ai/claude-code - Auth: run
claudeonce to log in (browser OAuth for Pro/Max, or setANTHROPIC_API_KEY) - Console auth:
claude auth login --consolefor API key billing - SSO auth:
claude auth login --ssofor Enterprise - Check status:
claude auth status(JSON) orclaude auth status --text(human-readable) - Health check:
claude doctor— checks auto-updater and installation health - Version check:
claude --version(requires v2.x+) - Update:
claude updateorclaude upgrade
Two Orchestration Modes
Hermes interacts with Claude Code in two fundamentally different ways. Choose based on the task.
Mode 1: Print Mode (-p) — Non-Interactive (PREFERRED for most tasks)
Print mode runs a one-shot task, returns the result, and exits. No PTY needed. No interactive prompts. This is the cleanest integration path.
terminal(command="claude -p 'Add error handling to all API calls in src/' --allowedTools 'Read,Edit' --max-turns 10", workdir="/path/to/project", timeout=120)
When to use print mode:
- One-shot coding tasks (fix a bug, add a feature, refactor)
- CI/CD automation and scripting
- Structured data extraction with
--json-schema - Piped input processing (
cat file | claude -p "analyze this") - Any task where you don't need multi-turn conversation
Print mode skips ALL interactive dialogs — no workspace trust prompt, no permission confirmations. This makes it ideal for automation.
Mode 2: Interactive PTY via tmux — Multi-Turn Sessions
Interactive mode gives you a full conversational REPL where you can send follow-up prompts, use slash commands, and watch Claude work in real time. Requires tmux orchestration.
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.
- 17d ago Changed 9cf9b448e927
- 1mo ago Changed ec92e627db1f
- 1mo ago Changed · +9 lines 070a53e4bae0
- 1mo ago First seen · 746 lines · 16 tokens per session scan D 3fd7c81f2c6c
claude-code is a skill published in the GitHub repository NousResearch/hermes-agent (255,903 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 9,164 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
caveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
code-review
Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep…
github
Search and work with the user's GitHub repositories through GitHub's official MCP server.
git
Source-control safety for Git. Two rules apply whether or not you read the body. First, never commit, amend, push, tag, rebase, cherry-pick, revert, or reset --hard unless the user asked for that exact write in this session. An explicit request to create a new commit counts anywhere in the user's own task text, but it…