MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
The small-front-door principle and what counts as a tool-surface change.
Install Tool Surface Discipline
$ npx skills add jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jgravelle/jcodemunch-mcp tool-surface-discipline --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/jgravelle/jcodemunch-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/tool-surface-discipline .claude/skills/tool-surface-discipline && 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 "tool-surface-discipline" agent skill from https://github.com/jgravelle/jcodemunch-mcp/tree/main/.claude/skills/tool-surface-discipline into .claude/skills/tool-surface-discipline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-surface-discipline", 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/jgravelle/jcodemunch-mcp/tree/main/.claude/skills/tool-surface-disciplineType 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 jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jgravelle/jcodemunch-mcp tool-surface-discipline --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jgravelle/jcodemunch-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/tool-surface-discipline .agents/skills/tool-surface-discipline && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tool-surface-discipline" agent skill from https://github.com/jgravelle/jcodemunch-mcp/tree/main/.claude/skills/tool-surface-discipline into .agents/skills/tool-surface-discipline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-surface-discipline", 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 jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jgravelle/jcodemunch-mcp tool-surface-discipline --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jgravelle/jcodemunch-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/tool-surface-discipline .cursor/skills/tool-surface-discipline && 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 "tool-surface-discipline" agent skill from https://github.com/jgravelle/jcodemunch-mcp/tree/main/.claude/skills/tool-surface-discipline into .cursor/skills/tool-surface-discipline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-surface-discipline", 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/jgravelle/jcodemunch-mcp.git --path .claude/skills/tool-surface-discipline--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 jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jgravelle/jcodemunch-mcp tool-surface-discipline --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jgravelle/jcodemunch-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/tool-surface-discipline .gemini/skills/tool-surface-discipline && 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 "tool-surface-discipline" agent skill from https://github.com/jgravelle/jcodemunch-mcp/tree/main/.claude/skills/tool-surface-discipline into .gemini/skills/tool-surface-discipline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-surface-discipline", 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 jgravelle/jcodemunch-mcp tool-surface-disciplineInstalls 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 jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jgravelle/jcodemunch-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/tool-surface-discipline .github/skills/tool-surface-discipline && 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 "tool-surface-discipline" agent skill from https://github.com/jgravelle/jcodemunch-mcp/tree/main/.claude/skills/tool-surface-discipline into .github/skills/tool-surface-discipline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-surface-discipline", 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 jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jgravelle/jcodemunch-mcp tool-surface-discipline --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jgravelle/jcodemunch-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/tool-surface-discipline .opencode/skills/tool-surface-discipline && 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 "tool-surface-discipline" agent skill from https://github.com/jgravelle/jcodemunch-mcp/tree/main/.claude/skills/tool-surface-discipline into .opencode/skills/tool-surface-discipline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tool-surface-discipline", 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
tool-surface-discipline- GitHub stars
- 2.8k
- Token cost
- ~389 tokens
- SKILL.md length
- 163 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
The small-front-door principle and what counts as a tool-surface change.
- Tasks that involve MCP servers
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Tool Surface Discipline is an agent skill from jgravelle/jcodemunch-mcp. The small-front-door principle and what counts as a tool-surface change. Load in /feature step 3, in review, and before editing any tool name, argument, description or tier.
Its SKILL.md is about 390 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 MCP servers. It works with Model Context Protocol. The repository describes itself as: Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP…
When your agent uses it
- Tasks that involve MCP servers
Example prompts
- “/tool-surface-discipline”
What it can do on your machine
Read from SKILL.md and the folder at commit 970c457. 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
Tool Surface Discipline loads about 389 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 163 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 163 words (~389 tokens).
“Authority: docs/standard/STANDARD.md criterion 4; CLAUDE.md "Tool-description quality", "Codex tool-surface benchmark", "Tier-switch pricing"; tests/test_schema_budget.py, tests/test_counter_surface_stability.py, tests/test_description_smells.py; scripts/surface_diff.py.”
- name
- tool-surface-discipline
Files
Just SKILL.md in .claude/skills/tool-surface-discipline of jgravelle/jcodemunch-mcp.
Open the folder on GitHubat commit 970c457
Compare with similar skills
Tool Surface Discipline 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 |
|---|---|---|---|---|---|---|
| Tool Surface Discipline this skilljgravelle/jcodemunch-mcp | 2.8k | — | ~389 | Automated safety check: Pass | Custom licence | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Warp GUI to Agent CLI Migration
warpdotdev/warp
Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.
More from jgravelle/jcodemunch-mcp
All 10 skills in this repoRelease
jgravelle/jcodemunch-mcp
Publishing a jMunch release (jcodemunch-mcp, jdocmunch-mcp, jdatamunch-mcp, jragmunch-cli), reviewing/merging/closing PRs, and responding to the community.
Benchmark Methodology
jgravelle/jcodemunch-mcp
Rules for measuring or quoting any benchmark number in this repo.
Observatory
jgravelle/jcodemunch-mcp
Context for the jcodemunch-observatory weekly scorecard — what it tracks, the Monday 06:00 UTC cron, why scores must be pulled live rather than transcribed, the NestJS grade story, and the…
PR Description
jgravelle/jcodemunch-mcp
The PR title and body template, and the rules for any comment drafted for a reporter or contributor.
Changelog Format
jgravelle/jcodemunch-mcp
The shape of a CHANGELOG.md entry and heading in this repo. An agent skill from jgravelle/jcodemunch-mcp.
Claude Md Budget
jgravelle/jcodemunch-mcp
How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation.
Related
Works with
Categories
Questions about Tool Surface Discipline
What does Tool Surface Discipline do?
The small-front-door principle and what counts as a tool-surface change. Tool Surface Discipline is an agent skill from jgravelle/jcodemunch-mcp. The small-front-door principle and what counts as a tool-surface change.
When should I use Tool Surface Discipline?
Tool Surface Discipline fits situations like: tasks that involve MCP servers.
How do I install Tool Surface Discipline in Claude Code?
Run `npx skills add jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a claude-code`. Or copy the skill folder (.claude/skills/tool-surface-discipline in jgravelle/jcodemunch-mcp) into .claude/skills/tool-surface-discipline in your project. Claude Code loads it when a task matches its description.
How do I install Tool Surface Discipline in Codex?
Run `npx skills add jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a codex`. Or copy the skill folder (.claude/skills/tool-surface-discipline in jgravelle/jcodemunch-mcp) into .agents/skills/tool-surface-discipline in your project. Codex loads it when a task matches its description.
Can I use Tool Surface Discipline 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 jgravelle/jcodemunch-mcp --skill tool-surface-discipline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tool-surface-discipline, .gemini/skills/tool-surface-discipline, .github/skills/tool-surface-discipline and .opencode/skills/tool-surface-discipline in your project.
What does Tool Surface Discipline need to run?
SKILL.md names no scripts, command-line tools or credentials: Tool Surface Discipline is instructions for the agent only.
Does Tool Surface Discipline 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 Tool Surface Discipline 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 Tool Surface Discipline use?
Tool Surface Discipline 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 Tool Surface Discipline use?
About 389 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 Tool Surface Discipline?
Skills that share tags, products or a category with Tool Surface Discipline: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tool Surface Discipline?
jgravelle (a GitHub user) maintains it in jgravelle/jcodemunch-mcp, which has 2,754 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 11, 2026.
Source: jgravelle/jcodemunch-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.