Agent skill

Client Subagent Guidelines

by hyvanmielenpelit in hyvanmielenpelit/GnollHack

Subagent constraints specific to the GnollHack client repository.

Custom licenceAuto-check passedAgent Workflows

Install Client Subagent Guidelines

skills CLI
$ npx skills add hyvanmielenpelit/GnollHack --skill client-subagent-guidelines -a claude-code

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

GitHub CLI
$ gh skill install hyvanmielenpelit/GnollHack client-subagent-guidelines --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/hyvanmielenpelit/GnollHack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/client-subagent-guidelines .claude/skills/client-subagent-guidelines && 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
client-subagent-guidelines
GitHub stars
161
Token cost
~222 tokens
SKILL.md length
51 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Custom licence

At a glance

Subagent constraints specific to the GnollHack client repository.

  • Tasks that involve Subagents
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Client Subagent Guidelines is an agent skill from hyvanmielenpelit/GnollHack. Subagent constraints specific to the GnollHack client repository. Covers the three build dependency chains that must not be parallelized across -- makedefs to generated headers to C interop, des files to levcomp to dlb, and GnollHackX XAML to makedefsdroid to GnollHackM -- and why cross-layer interop work in this repository escalates to the deep tier far more often than elsewhere. Read when writing a plan's Subagent Use section for GnollHack.

Its SKILL.md is about 220 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 Subagents. It works with C#. The repository describes itself as: Modern evolution of the classic roguelike game NetHack.

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/client-subagent-guidelines”

What it can do on your machine

Read from SKILL.md and the folder at commit 9df8a69. 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.

    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

Client Subagent Guidelines loads about 222 tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 51 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~222

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 51 words (~222 tokens).

“The full skill lives in this repository's tool-neutral agent directory (.agents/), which is shared with other AI coding agents. This file is only a pointer.”

— opening of SKILL.md by hyvanmielenpelit, Custom licence
name
client-subagent-guidelines

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/client-subagent-guidelines of hyvanmielenpelit/GnollHack.

Open the folder on GitHubat commit 9df8a69

Compare with similar skills

Client Subagent Guidelines 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.

Client Subagent Guidelines compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Client Subagent Guidelines this skillhyvanmielenpelit/GnollHack161—~222Automated safety check: PassCustom licence
Claude Code Agent Developmentanthropics/claude-plugins-official38k7 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25840 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 40 repos~1.5k tokens
    Agent WorkflowsAuto-check passed
  • Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed
  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from hyvanmielenpelit/GnollHack

All 11 skills in this repo
  • Client Implementation Planning

    hyvanmielenpelit/GnollHack

    Implementation planning overlay for the GnollHack client repository.

    161 GitHub stars~238 tokensUpdated 2 days ago
    Auto-check passed
  • Sentry Crash Analysis

    hyvanmielenpelit/GnollHack

    Systematic methodology for diagnosing GnollHack crash reports from the Sentry MCP server.

    161 GitHub stars~222 tokensUpdated 2 days ago
    Auto-check passed
  • Adding Game Content

    hyvanmielenpelit/GnollHack

    Patterns for adding monsters, objects, and artifacts to GnollHack.

    161 GitHub stars~169 tokensUpdated 2 days ago
    Auto-check passed
  • Build Pipeline

    hyvanmielenpelit/GnollHack

    Guide on building GnollHack native C libraries, processing assets with makedefs/levcomp/dgncomp/dlb, packaging nhdat, and compiling the C .NET MAUI frontend for Android, iOS, and Windows.

    161 GitHub stars~147 tokensUpdated 2 days ago
    Auto-check passed
  • C Code Documentation

    hyvanmielenpelit/GnollHack

    Best practices for AI agents documenting the GnollHack C codebase.

    161 GitHub stars~164 tokensUpdated 2 days ago
    Auto-check passed
  • Csharp Code Documentation

    hyvanmielenpelit/GnollHack

    Best practices for AI agents documenting the GnollHack C .NET MAUI codebase.

    161 GitHub stars~166 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Client Subagent Guidelines

What does Client Subagent Guidelines do?

Subagent constraints specific to the GnollHack client repository. Client Subagent Guidelines is an agent skill from hyvanmielenpelit/GnollHack. Subagent constraints specific to the GnollHack client repository.

When should I use Client Subagent Guidelines?

Client Subagent Guidelines fits situations like: tasks that involve Subagents.

How do I install Client Subagent Guidelines in Claude Code?

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

How do I install Client Subagent Guidelines in Codex?

Run `npx skills add hyvanmielenpelit/GnollHack --skill client-subagent-guidelines -a codex`. Or copy the skill folder (.claude/skills/client-subagent-guidelines in hyvanmielenpelit/GnollHack) into .agents/skills/client-subagent-guidelines in your project. Codex loads it when a task matches its description.

Can I use Client Subagent Guidelines 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 hyvanmielenpelit/GnollHack --skill client-subagent-guidelines -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/client-subagent-guidelines, .gemini/skills/client-subagent-guidelines, .github/skills/client-subagent-guidelines and .opencode/skills/client-subagent-guidelines in your project.

What does Client Subagent Guidelines need to run?

SKILL.md names no scripts, command-line tools or credentials: Client Subagent Guidelines is instructions for the agent only.

Does Client Subagent Guidelines 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 Client Subagent Guidelines 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 Client Subagent Guidelines use?

Client Subagent Guidelines has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Client Subagent Guidelines use?

About 222 tokens (SKILL.md is roughly 888 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 Client Subagent Guidelines?

Skills that share tags, products or a category with Client Subagent Guidelines: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (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 Client Subagent Guidelines?

hyvanmielenpelit (a GitHub organization) maintains it in hyvanmielenpelit/GnollHack, which has 161 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

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