Agent Toolkit

agent-toolkit

A collection of project-agnostic, generic agentic tools for common engineering tasks such as ticket refinement, planning, code reviews, agent memory hygiene, skill authoring, and more.

• Rules: generic behavioral rules I apply at user level across all projects. Each file in rules/ is a single, self-contained rule.
• Skills: skills I reuse across projects. Each lives in its own directory under skills/ with a SKILL.md describing its trigger, allowed tools, and steps.

Quick Install / Update

Install in one command:

git clone https://github.com/FrancescoBorzi/agent-toolkit.git && cd agent-toolkit && ./install.sh

Update in one command:

cd agent-toolkit && git pull && ./install.sh

Install via symlinks

install.sh symlinks every rule and skill from this repo into your user's config.

This means the skills and rules will automatically be available in all your projects without copying files around.

By default rules go to ~/.claude/rules and skills to ~/.claude/skills, but you can easily override this.

First clone the repo (or your own fork):

git clone https://github.com/FrancescoBorzi/agent-toolkit.git && cd agent-toolkit

Then you can run:

./install.sh

This will link all rules and all skills. To customize, use the options below:

./install.sh --rules-only            # link rules only
./install.sh --skills-only           # link skills only
./install.sh --skills-dir DIR        # custom skills destination (e.g. a project's .claude/skills)
./install.sh --rules-dir DIR         # custom rules destination
./install.sh --force                 # overwrite existing files/symlinks
./install.sh --help

Each rule and skill is linked individually.

You can also skip the script and symlink just the ones you want by hand:

ln -s "$(pwd)/rules/no-nonsense-comments.md" ~/.claude/rules/
ln -s "$(pwd)/skills/run-nx-checks"          ~/.claude/skills/

Start a new session and run /context to confirm everything is loaded. Rules and skills apply at the user level (all projects); to scope them to one project, symlink into that repo's .claude/rules/ or .claude/skills/ instead.

Install with agentwheel

agentwheel installs this repo's rules and skills into your agent and keeps them in sync across Claude, Codex, Copilot, and other runtimes, from one source. This repo ships an openpack.json manifest, so it's a first-class OpenPack package (requires agentwheel ≥ 0.9.0). Run it from where you want it installed (~ for user level, or a project root):

npx agentwheel install github:FrancescoBorzi/agent-toolkit --adapter claude

Swap --adapter claude for codex, copilot, etc. to target other agents. For dry runs, tracking updates, named targets, profiles, or more controlled add → plan → install flows, see the agentwheel documentation.

Only want specific pieces instead of everything? Select them by <type>/<name>, for example one skill plus one rule:

npx agentwheel install github:FrancescoBorzi/agent-toolkit --adapter claude \
  --select skills/run-nx-checks,rules/no-nonsense-comments.md

--select is repeatable or comma-separated.

The manifest also marks hard internal dependencies. For example, selecting skills/self-improve also installs skills/compact-skill-creator; selecting skills/memory-doctor also installs skills/self-improve; and selecting rules/self-improve-on-correction.md also installs skills/self-improve.

Artifact relationships

Some skills and rules form a workflow or rely on each other. Hard dependencies are encoded in openpack.json; suggested next steps remain documented in the skill text.

flowchart TD
  fetch_ticket["fetch-ticket"] --> refine["refine-ticket"]
  fetch_pr["fetch-pr-review"] --> refine
  refine --> manual["create-manual-test-instructions"]
  refine --> plan["create-implementation-plan"]

  self_rule["self-improve-on-correction rule"] --> self["self-improve"]
  self --> compact["compact-skill-creator"]
  memory_doctor["memory-doctor"] --> self
  compact_gov["compact-governing-docs rule"] --> compact

  plans_rule["plans-directory rule"] -. informs .-> fetch_ticket
  plans_rule -. informs .-> fetch_pr
  plans_rule -. informs .-> refine
  plans_rule -. informs .-> manual
  plans_rule -. informs .-> plan

  docs_rule["self-contained-docs rule"] -. informs .-> fetch_ticket
  docs_rule -. informs .-> fetch_pr
  docs_rule -. informs .-> refine
  docs_rule -. informs .-> manual
  docs_rule -. informs .-> plan

Install skills via skills.sh

You can also use the skills.sh installer to install the skills from this repo:

npx skills add FrancescoBorzi/agent-toolkit

Install skills via Claude Code plugin marketplace