Orca CLI
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
AI-native cross-session user modeling — builds a persistent, growing model of who you are, your expertise, preferences, and working style across all Claude sessions.
Install Honcho
$ npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AlexAI-MCP/hermes-CCC honcho --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/honcho .claude/skills/honcho && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "honcho" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/honcho into .claude/skills/honcho/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "honcho", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/honchoType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AlexAI-MCP/hermes-CCC honcho --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/honcho .agents/skills/honcho && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "honcho" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/honcho into .agents/skills/honcho/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "honcho", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AlexAI-MCP/hermes-CCC honcho --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/honcho .cursor/skills/honcho && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "honcho" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/honcho into .cursor/skills/honcho/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "honcho", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AlexAI-MCP/hermes-CCC.git --path skills/honcho--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AlexAI-MCP/hermes-CCC honcho --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/honcho .gemini/skills/honcho && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "honcho" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/honcho into .gemini/skills/honcho/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "honcho", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AlexAI-MCP/hermes-CCC honchoInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/honcho .github/skills/honcho && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "honcho" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/honcho into .github/skills/honcho/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "honcho", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AlexAI-MCP/hermes-CCC honcho --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/honcho .opencode/skills/honcho && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "honcho" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/honcho into .opencode/skills/honcho/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "honcho", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
honcho- GitHub stars
- 135
- Token cost
- ~1.3k tokens
- SKILL.md length
- 295 words
- Files
- 1
- Skills in repo
- 44
- Repo updated
- First seen
- Licence
- MIT
At a glance
AI-native cross-session user modeling — builds a persistent, growing model of who you are, your expertise, preferences, and working style across all Claude sessions.
- Works in 4 steps: New expertise demonstrated? → New tools or projects mentioned? → Communication preferences revealed? → …
- Tasks that involve Session handoff
- SKILL.md covers Philosophy, hermes-CCC Implementation, Commands and How Claude Uses the Profile, plus 1 more section
- Calls pip
What it does
Honcho is an agent skill from AlexAI-MCP/hermes-CCC. AI-native cross-session user modeling — builds a persistent, growing model of who you are, your expertise, preferences, and working style across all Claude sessions.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Session handoff. The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.
When your agent uses it
- Tasks that involve Session handoff
Example prompts
- “/honcho”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- New expertise demonstrated?
- New tools or projects mentioned?
- Communication preferences revealed?
- New recurring topics?
What it can do on your machine
Read from SKILL.md and the folder at commit 8107e89. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
docs.honcho.dev
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Honcho loads about 1.3k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 295 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 295 words, ~1,255 tokens.
Download SKILL.mdSave it as
.claude/skills/honcho/SKILL.md (or your agent's skills folder).- name
- honcho
- description
- AI-native cross-session user modeling — builds a persistent, growing model of who you are, your expertise, preferences, and working style across all Claude sessions.
- version
- 1.0.0
- author
- hermes-CCC (ported from Hermes Agent by NousResearch)
- license
- MIT
Honcho — Cross-Session User Modeling
"The agent that grows with you." Honcho builds a persistent model of who you are across every session — your expertise, communication style, recurring topics, and working preferences.
Philosophy
Unlike simple memory (saving facts), Honcho models the user as a person — updating its understanding through dialectic reasoning: observing patterns, forming hypotheses about your preferences, and refining them over time.
This is the core of what makes Hermes Agent feel like it "knows" you.
hermes-CCC Implementation
In hermes-CCC, Honcho runs as a structured user profile in the memory system. Full Honcho (honcho.dev) adds a cloud backend with dialectic reasoning.
User Profile Structure
Profile stored at: ~/.claude/projects/*/memory/user_honcho_profile.md
---
name: honcho-user-profile
type: user
description: Cross-session user model built by Honcho
updated: 2026-04-07
---
## Identity
- Name: [inferred or stated]
- Role: [developer / researcher / executive / etc.]
- Timezone: [UTC+9 / Korea]
- Primary language: [Korean/English]
## Expertise
- Deep expertise: [Python, AI/ML, ontology design, business strategy]
- Intermediate: [Next.js, Neo4j, blockchain]
- Learning: [Rust, Solana]
## Communication Style
- Preferred verbosity: terse (skip explanations I know)
- Output format: code-first, then explanation
- Language mix: Korean for strategy, English for code
- Tone: direct, no fluff
## Working Patterns
- Session length: typically 2-4 hours
- Recurring projects: [OpenCrab SaaS, hermes-CCC, Ontology workspace]
- Tools always in use: [Claude Code, Discord, Obsidian, Neo4j, LM Studio]
- Peak hours: [evening KST]
## Recurring Interests
- Multi-agent systems and orchestration
- Knowledge graphs / ontology
- AI infrastructure (vLLM, GRPO training)
- SaaS monetization strategy
## Preferences
- Never explain basics I already know
- Always show full code, not snippets
- When blocked, say so immediately
- Prioritize speed over perfection on first pass
- Delegate heavy builds to Codex
## Session History Patterns
- Often starts: checking project status
- Common requests: code generation, architecture review, Discord automation
- Frequently uses: /hermes-route, /hermes-memory, codex:rescueCommands
/honcho profile
Display the current user model. Claude reads the profile and summarizes key facts about how it understands you.
/honcho update
After a session, analyze what was discussed and update the profile:
- New expertise demonstrated?
- New tools or projects mentioned?
- Communication preferences revealed?
- New recurring topics?
Then write updates to user_honcho_profile.md.
/honcho calibrate
Run a quick 5-question calibration:
- What's your primary role?
- What are your strongest technical areas?
- How do you prefer explanations? (terse/detailed)
- What projects are you currently working on?
- Any specific preferences for how I should behave?
/honcho reset
Clear the user model and start fresh.
/honcho export
Export profile as JSON for backup or transfer.
How Claude Uses the Profile
When Honcho profile is loaded, Claude should:
- Skip explanations of tools/concepts the user knows deeply
- Use preferred verbosity level in all responses
- Reference current projects when suggesting approaches
- Adapt language mix (Korean/English as preferred)
- Assume expertise level from profile when writing code
- Prioritize working patterns (e.g., "delegate to Codex")
Full Honcho Integration (Optional)
For cloud-backed dialectic reasoning:
pip install honcho-aifrom honcho import Honcho
honcho = Honcho(app_id="your-app-id", api_key="your-api-key")
# Create/get user session
user = honcho.apps.users.get_or_create(app_id="hermes-ccc", name="alexlee")
session = honcho.apps.users.sessions.create(app_id="hermes-ccc", user_id=user.id)
# Add observation
honcho.apps.users.sessions.messages.create(
app_id="hermes-ccc",
user_id=user.id,
session_id=session.id,
is_user=True,
content="User prefers terse responses with code-first approach"
)
# Dialectic inference — Honcho reasons about the user
response = honcho.apps.users.sessions.chat(
app_id="hermes-ccc",
user_id=user.id,
session_id=session.id,
query="What communication style does this user prefer?"
)
print(response.content)See docs.honcho.dev for full API reference.
© AlexAI-MCP, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/honcho of AlexAI-MCP/hermes-CCC.
Open the folder on GitHubat commit 8107e89
Compare with similar skills
Honcho next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Honcho this skillAlexAI-MCP/hermes-CCC | 135 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Orca CLIstablyai/orca | 89k | 2 repos | ~593 | Automated safety check: Pass | MIT | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Session History Searchslopus/happy | 24k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Paseo Agent Handoffgetpaseo/paseo | 20k | 1 repos | ~606 | Automated safety check: Pass | Custom licence | |
| Memori Long-Term MemoryMemoriLabs/Memori | 17k | — | ~2k | Automated safety check: Notes | Custom licence |
Similar skills
Beads Task Memory
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
Session History Search
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
Paseo Agent Handoff
getpaseo/paseo
Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.
Memori Long-Term Memory
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
Beads
liwp/again
A skill your agent uses when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory.
More from AlexAI-MCP/hermes-CCC
All 44 skills in this repoGitHub Code Review
AlexAI-MCP/hermes-CCC
Review GitHub pull requests with a findings-first engineering mindset.
GitHub PR Workflow
AlexAI-MCP/hermes-CCC
Run a disciplined GitHub pull request workflow from branch creation through merge.
Hermes Memory
AlexAI-MCP/hermes-CCC
Manage durable project memory for Claude Code. An agent skill from AlexAI-MCP/hermes-CCC.
Hermes Route
AlexAI-MCP/hermes-CCC
Route Claude Code work by complexity, risk, and tool needs. An agent skill from AlexAI-MCP/hermes-CCC.
Hermes Skill
AlexAI-MCP/hermes-CCC
Create, improve, inventory, and audit Claude Code skills. An agent skill from AlexAI-MCP/hermes-CCC.
Hermes Traj
AlexAI-MCP/hermes-CCC
Capture Claude Code interaction trajectories in training-friendly formats.
Related
Categories
Questions about Honcho
What does Honcho do?
AI-native cross-session user modeling — builds a persistent, growing model of who you are, your expertise, preferences, and working style across all Claude sessions. Honcho is an agent skill from AlexAI-MCP/hermes-CCC. AI-native cross-session user modeling — builds a persistent, growing model of who you are, your expertise, preferences, and working style across all Claude sessions.
When should I use Honcho?
Honcho fits situations like: tasks that involve Session handoff.
How do I install Honcho in Claude Code?
Run `npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a claude-code`. Or copy the skill folder (skills/honcho in AlexAI-MCP/hermes-CCC) into .claude/skills/honcho in your project. Claude Code loads it when a task matches its description.
How do I install Honcho in Codex?
Run `npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a codex`. Or copy the skill folder (skills/honcho in AlexAI-MCP/hermes-CCC) into .agents/skills/honcho in your project. Codex loads it when a task matches its description.
Can I use Honcho in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlexAI-MCP/hermes-CCC --skill honcho -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/honcho, .gemini/skills/honcho, .github/skills/honcho and .opencode/skills/honcho in your project.
What does Honcho need to run?
Going by SKILL.md and its folder, Honcho needs the command-line tools its instructions call (pip). Our summary lists: Python 3.
Does Honcho access the network?
SKILL.md names 1 domain. As links in the text: docs.honcho.dev. This is read from the text; nothing was executed.
Is Honcho safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Honcho use?
Honcho is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Honcho use?
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Honcho?
Skills that share tags, products or a category with Honcho: Orca CLI (stablyai/orca, 89k stars), Beads Task Memory (gastownhall/beads, 28k stars), Session History Search (slopus/happy, 24k stars) and Paseo Agent Handoff (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Honcho?
AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.
Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.