New: 98,000+ 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

Grond

by TheOrcDev in TheOrcDev/skills

One word, GROND, and the agent stages everything, commits it, gets it onto the default branch, pushes, and reports every step in orc voice.

No licenceAuto-check: warnings

Install Grond

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add TheOrcDev/skills --skill grond -a claude-code

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

GitHub CLI
$ gh skill install TheOrcDev/skills grond --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/TheOrcDev/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/grond .claude/skills/grond && 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
grond
GitHub stars
106
Token cost
~1.3k tokens
SKILL.md length
620 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
None found

At a glance

One word, GROND, and the agent stages everything, commits it, gets it onto the default branch, pushes, and reports every step in orc voice.

  • Works in 7 steps: Find the gate → Check the ram for poison → Load everything → …
  • The user says GROND
  • SKILL.md covers The swing, The report and Stand down
  • Calls git

What it does

Grond is an agent skill from TheOrcDev/skills. One word, GROND, and the agent stages everything, commits it, gets it onto the default branch, pushes, and reports every step in orc voice. Saying GROND is the authorization, so the agent never asks for confirmation. Use when the user says "GROND", "grond it", "smash it to main", or invokes /grond.

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.

The repository describes itself as: Skills for True Dev Warriors.

When your agent uses it

  • The user says GROND
  • Smash it to main

Example prompts

  • “grond it”
  • “smash it to main”
  • “/grond”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Find the gate
  2. Check the ram for poison
  3. Load everything
  4. One commit, real message
  5. Get it onto the default branch
  6. Push
  7. Prove the gate fell

What it can do on your machine

Read from SKILL.md and the folder at commit bb7eaa5. 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:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Grond loads about 1.3k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 620 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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: warnings

The automated check found patterns that need a careful read before installing.

  • NoteMentions a .env fileSKILL.md:41
    secrets that do not belong in history: `.env` and its
  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:42
    v.example` is fine), `*.pem`, `*.key`, `id_rsa`, `*.p12`,

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 620 words (~1,259 tokens).

“The hammer of the underworld. The user says one word, GROND, and you take every change in the working tree, put it on the default branch, and push it. No plan, no confirmation prompt, no "are you sure". The word…”

— opening of SKILL.md by TheOrcDev
name
grond

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/grond of TheOrcDev/skills.

Open the folder on GitHubat commit bb7eaa5

Compare with similar skills

Grond 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.

Grond compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Grond this skillTheOrcDev/skills106—~1.3kAutomated safety check: WarnNone
Commitsickn33/agentic-awesome-skills47k2 repos~1.3kAutomated safety check: PassMIT
Commit Stagedfcakyon/claude-codex-settings1.2k—~643Automated safety check: PassApache-2.0
Commitantiwork/gumroad9.8k—~503Automated safety check: PassMIT
Commitdavila7/claude-code-templates32k3 repos~730Automated safety check: PassMIT
Commitwindmill-labs/windmill18k—~447Automated safety check: PassCustom licence

Similar skills

  • Commit

    sickn33/agentic-awesome-skills

    ALWAYS use this skill when committing code changes — never commit directly without it.

    47k GitHub starsUsed in 2 repos~1.3k tokens
    DevelopmentAuto-check passed

  • Commit Staged

    fcakyon/claude-codex-settings

    This skill should be used when user asks to "commit these changes", "write commit message", "stage and commit", "create a commit", "commit staged files", or explicitly invokes "commit-staged".

    1.2k GitHub stars~643 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Commit

    antiwork/gumroad

    Stage and commit changes with a clear, concise commit message.

    9.8k GitHub stars~503 tokensUpdated today
    DevelopmentAuto-check passed

  • Commit

    davila7/claude-code-templates

    Create commit messages following Sentry conventions. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 3 repos~730 tokens
    DevelopmentAuto-check passed

  • Commit

    windmill-labs/windmill

    Create a git commit with conventional commit format. An agent skill from windmill-labs/windmill.

    18k GitHub stars~447 tokensUpdated today
    DevelopmentAuto-check passed

  • Ghost Commit Workflow

    TryGhost/Ghost

    Guides the agent through making a focused git commit in the Ghost repository: inspect state, stage only relevant files, follow the contributing rules, then verify.

    55k GitHub stars~286 tokensUpdated today
    DevelopmentAuto-check passed

More from TheOrcDev/skills

All 17 skills in this repo

  • Intro Video

    TheOrcDev/skills

    Build Remotion intro, reel, and brand-film videos with remocn and ASR-timed captions.

    106 GitHub stars~1.6k tokensUpdated 10 days ago
    Auto-check passed

  • Living Backdrop

    TheOrcDev/skills

    Turn one still image into a living web backdrop - depth parallax that follows the pointer, a subject that breathes, and ambient wind, cloud drift, light and dust, in a single WebGL shader with a…

    106 GitHub stars~2.3k tokensUpdated 10 days ago
    Auto-check passed

  • Rig It

    TheOrcDev/skills

    Rig and animate game characters that actually hold up in-engine.

    106 GitHub stars~1.6k tokensUpdated 10 days ago
    Auto-check passed

  • Creature Animation

    TheOrcDev/skills

    Author, gate, preview and install production animation sets for Final Stand creatures (quadrupeds, arthropods, flyers, hybrids) using the Plan 009 pipeline in tools/3d/animationquality/creatures.

    106 GitHub stars~858 tokensUpdated 10 days ago
    Auto-check passed

  • Cut It

    TheOrcDev/skills

    Cut an existing plan into ordered, self-contained slices (execution phases) sized for an AI agent to pick up and run one at a time.

    106 GitHub stars~753 tokensUpdated 10 days ago
    Auto-check passed

  • GitHub To Origin

    TheOrcDev/skills

    Agent runbook for moving a repository from GitHub to Cursor Origin code hosting, including repointing Vercel so production keeps deploying.

    106 GitHub stars~2k tokensUpdated 10 days ago
    Auto-check passed

Questions about Grond

What does Grond do?

One word, GROND, and the agent stages everything, commits it, gets it onto the default branch, pushes, and reports every step in orc voice. Grond is an agent skill from TheOrcDev/skills. One word, GROND, and the agent stages everything, commits it, gets it onto the default branch, pushes, and reports every step in orc voice.

When should I use Grond?

Grond fits situations like: the user says GROND; smash it to main.

How do I install Grond in Claude Code?

Run `npx skills add TheOrcDev/skills --skill grond -a claude-code`. Or copy the skill folder (skills/grond in TheOrcDev/skills) into .claude/skills/grond in your project. Claude Code loads it when a task matches its description.

How do I install Grond in Codex?

Run `npx skills add TheOrcDev/skills --skill grond -a codex`. Or copy the skill folder (skills/grond in TheOrcDev/skills) into .agents/skills/grond in your project. Codex loads it when a task matches its description.

Can I use Grond 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 TheOrcDev/skills --skill grond -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grond, .gemini/skills/grond, .github/skills/grond and .opencode/skills/grond in your project.

What does Grond need to run?

Going by SKILL.md and its folder, Grond needs the command-line tools its instructions call (git).

Does Grond access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Grond safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Grond use?

No licence was found for Grond or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Grond 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 Grond?

Skills that share tags, products or a category with Grond: Commit (sickn33/agentic-awesome-skills, 47k stars), Commit Staged (fcakyon/claude-codex-settings, 1.2k stars), Commit (antiwork/gumroad, 9.8k stars) and Commit (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Grond?

TheOrcDev (a GitHub user) maintains it in TheOrcDev/skills, which has 106 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 28, 2026.

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