New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hermes Agent One-Shot Delegation

by CherryHQ in CherryHQ/cherry-studio

Runs Hermes Agent once for a bounded local task, with warnings about its automatic tool approval and advice to use a disposable copy for read-only work.

AGPL-3.0Auto-check passedAgent Workflows

Install Hermes Agent One-Shot Delegation

skills CLI
$ npx skills add CherryHQ/cherry-studio --skill code-mate-hermes -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CherryHQ/cherry-studio code-mate-hermes --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/code-cli-skills/code-mate-hermes .claude/skills/code-mate-hermes && rm -rf skills-src

Use ~/.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/

Facts

Skill name
code-mate-hermes
GitHub stars
52k
Token cost
~390 tokens
SKILL.md length
213 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Runs Hermes Agent once for a bounded local task, with warnings about its automatic tool approval and advice to use a disposable copy for read-only work.

  • Works in 3 steps: Set the Bash working directory to the… → Check availability with command -v… → Run one task and exit
  • Delegating a task to Hermes after you have accepted its automatic approvals
  • SKILL.md covers Run and Authentication And Permissions
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hermes Agent runs in one-shot mode through `hermes -z`, and this skill covers using it safely when you explicitly ask for work to go to it and accept how it approves tools. The agent sets the shell to the smallest directory you authorized, applies a finite timeout of normally 10 minutes, and checks that the `hermes` command exists.

Output is final text on stdout, with exit zero for success, one for failure or no response, and two for invalid arguments or an empty failed or partial result. The key warning is that one-shot mode switches on YOLO and hook acceptance by itself and can load tools, memory, rules and `AGENTS.md`. Read-only jobs therefore belong in a disposable or read-only copy, and runs against the real project need an explicit request, a narrow prompt and directory, and a diff check afterward.

When your agent uses it

  • Delegating a task to Hermes after you have accepted its automatic approvals
  • Letting Hermes edit a few named files in an authorized project
  • Running Hermes against a throwaway copy of a repository for analysis

Example prompts

  • “Delegate this to Hermes: update the README install section in ./docs only, then show me the diff.”
  • “Run Hermes on a disposable copy of the repo and summarize why the linter fails.”
  • “I accept Hermes auto-approving tools. Have it fix the typo in src/cli.ts and nothing else.”

Requirements

  • Hermes Agent installed through Code Mate
  • Provider and model configured in Code Mate

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Set the Bash working directory to the smallest directory the user authorized and set a finite timeout, normally 10 minutes.
  2. Check availability with command -v hermes. If it is missing, stop and ask the user to install Hermes Agent in Code Mate.
  3. Run one task and exit

What it can do on your machine

Read from SKILL.md and the folder at commit dd0767e. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Hermes Agent One-Shot Delegation loads about 390 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 213 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~390

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 CherryHQ/cherry-studio at commit dd0767e, republished under its AGPL-3.0 licence (© CherryHQ). 213 words, ~390 tokens.

Download SKILL.mdSave it as .claude/skills/code-mate-hermes/SKILL.md (or your agent's skills folder).
name
code-mate-hermes
description
Runs Hermes Agent in one-shot mode for bounded local tasks. Use when the user explicitly asks to delegate work to Hermes and accepts its automatic tool approval behavior.

Hermes Agent

Run

  1. Set the Bash working directory to the smallest directory the user authorized and set a finite timeout, normally 10 minutes.
  2. Check availability with command -v hermes. If it is missing, stop and ask the user to install Hermes Agent in Code Mate.
  3. Run one task and exit:
bash
hermes -z "<prompt>"

Pass the prompt as one quoted argument. Treat stdout as final text. Exit zero means success, exit one means failure or no response, and exit two means invalid arguments or an empty failed/partial result. Never start the interactive UI or a login flow.

Authentication And Permissions

If Hermes reports missing provider, model, or API configuration, stop and ask the user to configure Hermes Agent in Code Mate. Never request, read, print, or copy credentials.

One-shot mode automatically enables YOLO and hook acceptance and can load tools, memory, rules, and AGENTS.md. Do not run it in a writable project for read-only work. Use a disposable or read-only copy instead. Run it against the real project only when the user explicitly requests workspace changes, constrain the directory and prompt, and inspect the diff afterward.

Example: for an approved edit, ask Hermes to touch only named files, run it in that project, require exit zero, and inspect the resulting diff before reporting success.

© CherryHQ, AGPL-3.0. 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 resources/code-cli-skills/code-mate-hermes of CherryHQ/cherry-studio.

Open the folder on GitHubat commit dd0767e

Compare with similar skills

Hermes Agent One-Shot Delegation 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.

Hermes Agent One-Shot Delegation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hermes Agent One-Shot Delegation this skillCherryHQ/cherry-studio52k—~390Automated safety check: PassAGPL-3.0
Cline Pilotsickn33/agentic-awesome-skills47k1 repos~4.6kAutomated safety check: PassMIT
Kode Permissions DebuggingshareAI-lab/Kode-CLI5.2k—~498Automated safety check: PassApache-2.0
Sol and Luna Worker Routermajiayu000/spellbook286—~3.3kAutomated safety check: PassMIT
Spk Run Program Orchestratespec-kitty/spec-kitty1.7k—~209Automated safety check: PassMIT
Dispatch Agentsdanielvm-git/bigpowers256—~1.3kAutomated safety check: PassMIT

Similar skills

  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Agent WorkflowsAuto-check passed

  • Kode Permissions Debugging

    shareAI-lab/Kode-CLI

    Troubleshoots Kode permission prompts and denials, including allowlists, command-level tool limits, dontAsk mode and subagent inheritance, without loosening permissions.

    5.2k GitHub stars~498 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Sol and Luna Worker Router

    majiayu000/spellbook

    Splits substantial coding or repository-review work between a Sol commander that decides and verifies and a separate Luna Max worker that implements, with an auditable run log.

    286 GitHub stars~3.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Spk Run Program Orchestrate

    spec-kitty/spec-kitty

    Orchestrate multi-repo, multi-mission Spec Kitty programs across dependencies, parallel agents, review gates, merge, and post-merge closeout.

    1.7k GitHub stars~209 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Dispatch Agents

    danielvm-git/bigpowers

    Dispatch multiple subagents in parallel on independent tasks.

    256 GitHub stars~1.3k tokensUpdated 16 days ago
    Agent WorkflowsAuto-check passed

  • Ship Feature

    theexperiencecompany/gaia

    Autonomously ship a feature end-to-end with zero human intervention: plan it, implement it, review it with a team of subagents, boot the full stack, drive it in a real browser like a user…

    308 GitHub stars~2.7k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from CherryHQ/cherry-studio

All 30 skills in this repo

  • Office File Transform

    CherryHQ/cherry-studio

    Derives new files from a selected part of a spreadsheet, Word document, PDF or slide deck, such as a cell range, paragraph, page or slide, without ever modifying the source file.

    52k GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed

  • GitHub Issue Creator

    CherryHQ/cherry-studio

    Creates GitHub issues for the current repository by choosing the matching issue template and following its format, with a permission check for engineering tasks.

    52k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Cherry Studio PR Review

    CherryHQ/cherry-studio

    Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.

    52k GitHub stars~3.9k tokensUpdated yesterday
    Auto-check passed

  • Cherry Studio Regression Tests

    CherryHQ/cherry-studio

    Runs Cherry Studio's critical-path regression suite as deterministic Playwright E2E tests through a GitHub workflow on macOS and Windows runners.

    52k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Antigravity CLI Runner

    CherryHQ/cherry-studio

    Runs the Antigravity CLI headlessly with the agy command to analyze a repository or carry out a coding task, then checks its JSON result and the diff.

    52k GitHub stars~531 tokensUpdated yesterday
    Auto-check passed

  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    52k GitHub stars~504 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Hermes Agent One-Shot Delegation

What does Hermes Agent One-Shot Delegation do?

Runs Hermes Agent once for a bounded local task, with warnings about its automatic tool approval and advice to use a disposable copy for read-only work. Hermes Agent runs in one-shot mode through `hermes -z`, and this skill covers using it safely when you explicitly ask for work to go to it and accept how it approves tools. The agent sets the shell to the smallest directory you authorized, applies a finite timeout of normally 10 minutes, and checks that the `hermes` command exists.

When should I use Hermes Agent One-Shot Delegation?

Hermes Agent One-Shot Delegation fits situations like: delegating a task to Hermes after you have accepted its automatic approvals; letting Hermes edit a few named files in an authorized project; running Hermes against a throwaway copy of a repository for analysis.

How do I install Hermes Agent One-Shot Delegation in Claude Code?

Run `npx skills add CherryHQ/cherry-studio --skill code-mate-hermes -a claude-code`. Or copy the skill folder (resources/code-cli-skills/code-mate-hermes in CherryHQ/cherry-studio) into .claude/skills/code-mate-hermes in your project. Claude Code loads it when a task matches its description.

How do I install Hermes Agent One-Shot Delegation in Codex?

Run `npx skills add CherryHQ/cherry-studio --skill code-mate-hermes -a codex`. Or copy the skill folder (resources/code-cli-skills/code-mate-hermes in CherryHQ/cherry-studio) into .agents/skills/code-mate-hermes in your project. Codex loads it when a task matches its description.

Can I use Hermes Agent One-Shot Delegation 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 CherryHQ/cherry-studio --skill code-mate-hermes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-mate-hermes, .gemini/skills/code-mate-hermes, .github/skills/code-mate-hermes and .opencode/skills/code-mate-hermes in your project.

What does Hermes Agent One-Shot Delegation need to run?

SKILL.md names no scripts, command-line tools or credentials: Hermes Agent One-Shot Delegation is instructions for the agent only. Our summary lists: Hermes Agent installed through Code Mate; Provider and model configured in Code Mate.

Does Hermes Agent One-Shot Delegation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hermes Agent One-Shot Delegation 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 Hermes Agent One-Shot Delegation use?

Hermes Agent One-Shot Delegation is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hermes Agent One-Shot Delegation use?

About 390 tokens (SKILL.md is roughly 1.6k 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 Hermes Agent One-Shot Delegation?

Skills that share tags, products or a category with Hermes Agent One-Shot Delegation: Cline Pilot (sickn33/agentic-awesome-skills, 47k stars), Kode Permissions Debugging (shareAI-lab/Kode-CLI, 5.2k stars), Sol and Luna Worker Router (majiayu000/spellbook, 286 stars) and Spk Run Program Orchestrate (spec-kitty/spec-kitty, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hermes Agent One-Shot Delegation?

CherryHQ (a GitHub organization) maintains it in CherryHQ/cherry-studio, which has 52,407 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 7, 2026.

Source: CherryHQ/cherry-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.