agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when configuring settings.json to reduce fuse-commit-pro's context token usage.
$ npx -y skills add fusengine/agents --skill commit-optimization --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/commit-optimizationContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when configuring settings.json to reduce fuse-commit-pro's context token usage.
name: commit-optimization description: Use when configuring settings.json to reduce fuse-commit-pro's context token usage.
<objective> Documents the `includeGitInstructions: false` settings.json option (and its `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS=1` env var override, which takes precedence) that removes Claude Code's built-in commit/PR workflow instructions from the system prompt — saving 2-5% context tokens — since fuse-commit-pro supplies its own comprehensive git workflow that supersedes the defaults. </objective>
For best results with fuse-commit-pro, add this to your `~/.claude/settings.json`:
{
"includeGitInstructions": false
}This removes Claude Code's built-in commit/PR workflow instructions from the system prompt, saving 2-5% context tokens. fuse-commit-pro provides its own comprehensive git workflow that supersedes the defaults.
Note: `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS=1` env var takes precedence over this setting.
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).