Skip to content
Back to search

.claude

SkillWorks with Claude CodeGitHub

This repository contains my personal configuration settings for Claude Code, Anthropic's official CLI tool for coding.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/zacheryglass--claude/badge.svg)](/listings/zacheryglass--claude)

HTML

<a href="/listings/zacheryglass--claude"><img src="/api/listings/zacheryglass--claude/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 109 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Personal Claude Code Configuration
  2. This repository contains my personal configuration settings for [Claude Code](https://claude.ai/code).
  3. ## What is Claude Code?
  4. Claude Code is an interactive command-line interface that provides AI assistance for software development tasks.
  5. ## Repository Contents
  6. - **`settings.json`** - Core configuration file containing:
  7. - Permission settings for various tools and commands
  8. - Custom hooks for enhanced functionality
  9. - etc.
  10. - **`statusline.go`** - Custom status line (see [Statusline](#statusline) below). `build_statusline.sh` and `build_statusline.ps1` build it for Windows and macOS, and `statusline.cmd` runs the right binary on each.
  11. - **`CLAUDE.md`** - Minimal agent instructions
  12. - **`hooks/`** - Pre/Post-tool-use scripts:
  13. - `emoji_remover.py` - Post-edit hook that tells Claude to remove any emojis an edit adds
  14. - `emoji_remover.cmd` - Cross-platform wrapper that `settings.json` calls to run `emoji_remover.py` on Windows or macOS
  15. - `github_issue_guard.py` - Guard for GitHub issue interactions (not enabled in `settings.json`)
  16. - `protect_claude_md.py` - Protection for critical configuration files (not enabled in `settings.json`)
  17. - **`skills/`** - Reusable agent skills:
  18. - `gemini-agent` - Delegates arbitrary tasks to Gemini CLI for a second opinion or token savings.
  19. - `generate-goal` - Turns the current conversation into one self-contained `/goal` prompt, so a long discussion doesn't need summarizing by hand.
  20. - `git-worktree-prune` - Deletes stale git worktrees and local branches, keeping any that hold work found nowhere else.
  21. - `root-cause-tracing` - Traces a bug backward through the call stack, adding instrumentation as needed, to find the original trigger.
  22. - `run-goals` - Runs several `/goal` prompts in parallel as non-interactive Claude Code sessions, each in its own git worktree, and reports the results.
  23. - `skill-creator` - Scaffolds and refines new skills following the official skill authoring guidelines.
  24. - **`commands/`** - Custom slash commands:
  25. - `/arch-review` - Review architecture of specified paths or staged/unstaged git changes.
  26. - `/arewedone` - Run a structural completeness review on recent changes.
  27. - `/bugs` - Invoke the `bug-finder` agent to hunt for logical errors and runtime issues.
  28. - `/commit` - Draft a conventional commit from the current staged/unstaged diff.
  29. - `/docs` - Run the documentation review and implementation workflow.
  30. - `/perf-check` - Invoke the `performance-profiler` agent to analyze code for performance issues.
  31. - `/review-gauntlet` - Run all the standard review agents in parallel on current changes, then address their findings.
  32. - `/ui-review` - Invoke the `ui-ux-consultant` agent for a UI/UX and accessibility review.
  33. - **`agents/`** - Specialized sub-agents invoked via the Agent tool:
  34. - `architecture-reviewer` - Senior architect review of structural integrity, scalability, and long-term maintainability.
  35. - `bug-finder` - Hunts for logical errors, race conditions, and unhandled edge cases in a specific function or module.
  36. - `c-safety-reviewer` - Reviews changed C code for leaked memory, file descriptors and sockets, and for security vulnerabilities.
  37. - `compatibility-reviewer` - After a change to an interface, file format or config, finds the scripts, docs and other consumers that still expect the old one.
  38. - `doc-implementer` - Implements documentation changes based on review findings.
  39. - `doc-reviewer` - Analyzes documentation state and reports gaps, outdated content, and quality issues without making changes.
  40. - `git-cherry-pick-orchestrator` - Orchestrates cherry-pick operations across repositories with submodules via a plan-then-execute workflow.
  41. - `github-issue-creator` - Creates GitHub issues to track bugs, follow-ups, and future work identified mid-conversation.
  42. - `performance-profiler` - Diagnoses and fixes performance issues in desktop apps (slow UI, high memory, long startup).
  43. - `structural-completeness-reviewer` - Verifies that recent changes are fully integrated, old code is removed, and no technical debt was introduced.
  44. - `test-runner` - Runs the project's test suite and reports results.
  45. - `ui-ux-consultant` - Reviews desktop UI/UX and accessibility against platform standards.
  46. - **`sync-docs.py`** - Documentation synchronization utility
  47. ## Statusline
  48. `statusline.go` builds to a small binary that runs every second and renders a status bar. All data is cached to disk so git and file reads only happen when something actually changes.
  49. ### Performance
  50. Measured over 20 runs each on Windows 11 (see `tests/bench.ps1`):
  51. | Scenario | Median | Notes |
  52. | --------------------------- | ------ | --------------------------- |
  53. | Fully warm (all caches hit) | 16ms | typical tick |
  54. | Git cache miss (exec git) | 62ms | once per 10 min per cwd |
  55. | No git repo | 13ms | |
  56. | Pure binary startup | 11ms | floor: process + JSON parse |
  57. Full example:
  58. ```
  59. 📁 myproject | 🤖 Sonnet 4.6 (Medium) | ⚡ 12.3k/4.1k | ⏳ 47m 12s | 🌿 main*↑2 | 87% Remaining
  60. ```
  61. ### Segments
  62. | Segment | Example | Description |
  63. | --- | --- | --- |
  64. | Project | `📁 myproject` | Leaf name of `workspace.project_dir` (falls back to `current_dir`). |
  65. | Model + Effort | `🤖 Sonnet 4.6 (Medium)` | Display name of the active model, plus effort level in parentheses (hidden for Haiku). Effort is read from `settings.json` and cached by file mtime. |
  66. | Prompt Cache | `⚡ 12.3k/4.1k` | Cumulative cache read / write tokens for the session (read 12,300, wrote 4,100). Hidden when both are zero; small numbers shown without suffix. |
  67. | Cache Timer | `⏳ 47m 12s` | Counts down 60 minutes from the last API call. Shows `Expired` once the window passes and `No Cache` before the first call. Resets per model when you switch models. `/clear` or `/compact` resets all model timers. |
  68. | Git | `🌿 main*↑2` | Branch name with dirty/sync indicators: `*` for uncommitted changes, `↑N`/`↓N` for ahead/behind remote, `HEAD@<sha>` when detached. Only shown when `current_dir/.git` exists. Cached for 10 minutes per directory. |
  69. | Context remaining | `87% Remaining` | Percentage of context window still available, color-coded: green above 50%, yellow 20–50%, red below 20%. |
  70. ## Documentation
  71. For more information about Claude Code, see the official documentation:
  72. - [Overview](https://docs.anthropic.com/en/docs/claude-code/overview)
  73. - [Settings](https://docs.anthropic.com/en/docs/claude-code/settings)
  74. - [Agent Skills](https://code.claude.com/docs/en/skills)
  75. - [Slash Commands](https://docs.anthropic.com/en/docs/claude-code/slash-commands)
  76. - [Sub-agents](https://docs.anthropic.com/en/docs/claude-code/sub-agents)
  77. - [Hooks Guide](https://docs.anthropic.com/en/docs/claude-code/hooks-guide)
  78. ## Usage
  79. To use this configuration:
  80. 1. Clone this repository to your local machine
  81. 2. Copy the configuration files to your Claude Code settings directory (`~/.claude/`)
  82. 3. Adjust permissions and settings as needed for your development environment
  83. 4. Restart Claude Code to apply the new configuration

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.