Git Guardrails Claude Code
fossasia/eventyay-interpretation
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
$ npx skills add ntorga/agent-starter-kit --skill boot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ntorga/agent-starter-kit boot --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/ntorga/agent-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/boot .claude/skills/boot && 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 "boot" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/boot into .claude/skills/boot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boot", 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/ntorga/agent-starter-kit/tree/main/skills/bootType 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 ntorga/agent-starter-kit --skill boot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ntorga/agent-starter-kit boot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/boot .agents/skills/boot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "boot" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/boot into .agents/skills/boot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boot", 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 ntorga/agent-starter-kit --skill boot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ntorga/agent-starter-kit boot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/boot .cursor/skills/boot && 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 "boot" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/boot into .cursor/skills/boot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boot", 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/ntorga/agent-starter-kit.git --path skills/boot--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 ntorga/agent-starter-kit --skill boot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ntorga/agent-starter-kit boot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/boot .gemini/skills/boot && 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 "boot" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/boot into .gemini/skills/boot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boot", 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 ntorga/agent-starter-kit bootInstalls 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 ntorga/agent-starter-kit --skill boot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/boot .github/skills/boot && 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 "boot" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/boot into .github/skills/boot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boot", 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 ntorga/agent-starter-kit --skill boot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ntorga/agent-starter-kit boot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/boot .opencode/skills/boot && 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 "boot" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/boot into .opencode/skills/boot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boot", 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.
bootSession startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
Boot is an agent skill from ntorga/agent-starter-kit. Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
Its SKILL.md is about 940 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 AI & LLM Engineering. The repository describes itself as: The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) . The licence is MIT.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 851e942. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
gitbashFrom the folder's file list and the shell code blocks in SKILL.md.
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.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Boot loads about 937 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 430 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.
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.
The full file from ntorga/agent-starter-kit at commit 851e942, republished under its MIT licence (© ntorga). 430 words, ~937 tokens.
.claude/skills/boot/SKILL.md (or your agent's skills folder).Every session starts cold. The Maestro needs to ensure the project is wired correctly, the framework is up to date, load the project's rules, and understand the codebase before it can dispatch work effectively. This skill defines the boot sequence that brings the Maestro from zero to ready.
All framework files live under .agents/. Markdown references within the framework use bare paths for readability — always resolve them under .agents/. Shell commands always use the .agents/ prefix for project-root paths.
Gitignore. Ensure .agents/, .memory/, and opencode.json are in the project's .gitignore. Run:
touch .gitignore
for entry in '.agents/' '.memory/' 'opencode.json' '.ignore'; do
grep -qxF "$entry" .gitignore || echo "$entry" >> .gitignore
doneFramework pull. Run:
git -C .agents pullCHANGELOG.md in .agents to understand what changed..memory/long-term.md, read the changelog, and for each memory entry remove it only if the changelog describes a feature, skill, or rule that replaces that memory's purpose. If the entry's purpose is not clearly covered by the changelog, keep it.personas/maestro.md from the top so updated instructions take effect.Memory. Load memory (uses: skills/agent-memory/SKILL.md).
Core skills. Read the following core skills IN FULL now. These are mandatory for every dispatch and planning decision. Do not skip, summarize, or rely on memory:
skills/dispatch/SKILL.md — required for every sub-agent dispatchskills/plan-management/SKILL.md — required for planning decisions and epic trackingCLI configuration. Run:
bash .agents/skills/assets/maestro-boot-configure-cli.shcreated or updated, inform the user that agent bindings changed and they should restart the session for the new bindings to take effect.unchanged, no action is needed.yq or jq is not installed, the script prints a skip message — no action needed.Load the rules index. Read rules/README.md to know what rules are available and their scopes. Do not read the individual rule files — sub-agents will read them when dispatched.
Context. Verify the project has context files. Run:
find . -name ".context.md" -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/vendor/*" -not -path "*/.cache/*" -print -quitfind produces no output, no .context.md files exist. Dispatch the Contextualizer (uses: personas/contextualizer.md) before proceeding.docs/FEATURE-MAP.md — if it is missing, the Contextualizer dispatch covers it (uses: skills/context-maintenance/SKILL.md).Greet. Greet the user and wait for instructions. Remind the user: they are not talking to a single agent — they are talking to a team of specialists that can handle multiple requests simultaneously, so large and complex prompts are welcome.
.agents directory means outdated instructions.© ntorga, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/boot of ntorga/agent-starter-kit.
Open the folder on GitHubat commit 851e942
Boot 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 |
|---|---|---|---|---|---|---|
| Boot this skillntorga/agent-starter-kit | 146 | — | ~937 | Automated safety check: Pass | MIT | |
| Git Guardrails Claude Codefossasia/eventyay-interpretation | 1.6k | 12 repos | ~578 | Automated safety check: Pass | Apache-2.0 | |
| Codebase Managementgiancarloerra/SocratiCode | 3.3k | 1 repos | ~1.8k | Automated safety check: Pass | AGPL-3.0 | |
| Azure AI Projects Python SDKmicrosoft/skills | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT | |
| AI Research Reproductionlllllllama/RigorPilot-Skills | 497 | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Onnxtxtonnx/onnx | 22k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 |
fossasia/eventyay-interpretation
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
giancarloerra/SocratiCode
Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
lllllllama/RigorPilot-Skills
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.
onnx/onnx
Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.
strands-agents/harness-sdk
Identify documentation gaps and prioritize the docs backlog.
ntorga/agent-starter-kit
Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.
ntorga/agent-starter-kit
Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.
ntorga/agent-starter-kit
Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.
ntorga/agent-starter-kit
Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.
ntorga/agent-starter-kit
Browser inspection and interaction for verifying rendered web UI during development.
ntorga/agent-starter-kit
Reviews code and plans for logic coherence, correctness, and structural integrity.
Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet. Boot is an agent skill from ntorga/agent-starter-kit. Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
Boot fits situations like: AI & LLM Engineering work in your project.
Run `npx skills add ntorga/agent-starter-kit --skill boot -a claude-code`. Or copy the skill folder (skills/boot in ntorga/agent-starter-kit) into .claude/skills/boot in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ntorga/agent-starter-kit --skill boot -a codex`. Or copy the skill folder (skills/boot in ntorga/agent-starter-kit) into .agents/skills/boot in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ntorga/agent-starter-kit --skill boot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/boot, .gemini/skills/boot, .github/skills/boot and .opencode/skills/boot in your project.
Going by SKILL.md and its folder, Boot needs the command-line tools its instructions call (git and bash).
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.
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.
Boot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 937 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Boot: Git Guardrails Claude Code (fossasia/eventyay-interpretation, 1.6k stars), Codebase Management (giancarloerra/SocratiCode, 3.3k stars), Azure AI Projects Python SDK (microsoft/skills, 3.1k stars) and AI Research Reproduction (lllllllama/RigorPilot-Skills, 497 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ntorga (a GitHub user) maintains it in ntorga/agent-starter-kit, which has 146 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 12, 2026.
Source: ntorga/agent-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.