Agentics

CLI tools, slash commands, and workflows that put AI agents to work across the development lifecycle — from code review to workflow automation.

Subprojects

claude-commands

Custom slash commands for Claude Code that automate code review, refinement, design, PR feedback, daily activity notes, and ticket authoring.

Six commands that handle multi-phase workflows end-to-end:

Command	What it does
/review <PR>	Checks out a PR into an isolated worktree, runs lint/tests, performs deep code analysis across 9 severity levels, validates findings against actual code, and produces a numbered findings report. Never commits or pushes.
/refine	Discovers issues on the current branch (lint, tests, CI failures, PR comments), fixes them in up to 3 rounds, commits, pushes, creates/updates the PR, and watches CI.
/suggest <issues>	Posts specific findings from a /review report as inline PR comments with suggestion blocks. Detects stale reviews and deduplicates against existing comments.
/design <brief>	Explores the codebase, produces a 1-pager design doc with alternatives and comparison matrix, then breaks the solution into sequenced implementation tickets.
/daily [date]	Synthesizes your GitHub activity for a single day into an Obsidian daily note (## Activity + ## Standup), creating it from a template or updating in place. Local-write only. Needs a Configuration block (vault path, GitHub scope).
/ticket [url|desc]	Creates or updates a ClickUp ticket with a structured 3-section body (Description, Acceptance Criteria, Gotchas), resolving private-doc links to public URLs or inlining them. Needs a Configuration block (internal-docs path).

Commands share common reference files in shared/: pr-commands.md (argument parsing, project type detection, PR comment fetching), review-rubrics.md (security/architecture/test rubrics for /review and /refine), checkpoint.md (approval-gate protocol for /daily and /ticket), and design-templates.md (document structure).

Install & usage:

cd claude-commands && make deploy   # copies to ~/.claude/commands/ and ~/.claude/shared/

# Then in any Claude Code session:
/review 42
/refine
/suggest 1,3
/design "Add patient export API"
/daily                    # /daily and /ticket each read a Configuration block at the
/ticket "Fix flaky test"  # top of the command — set vault path / GitHub scope / internal-docs path first

Make target	What it does
make deploy	Copy commands and shared files to ~/.claude/
make diff	Show differences between repo and deployed files
make status	Check whether deployed files are in sync

This repo is the source of truth — never edit files directly in ~/.claude/.

---

precommit-agentic-check

LLM-powered pre-commit gate that reviews staged git changes against a policy prompt and returns a structured pass/fail verdict.

Reads your staged diff with surrounding context, sends it to an LLM with a policy prompt, and enforces a JSON response contract (pass/fail, findings with severity/file/line, optional suggested patch). Zero runtime dependencies — uses stdlib HTTP only.

Install & usage:

# .pre-commit-config.yaml
repos:
  - repo: local
    hooks:
      - id: agentic-check
        name: Agentic Check
        entry: agentic-check
        language: python
        pass_filenames: false
        additional_dependencies:
          - precommit-agentic-check==0.1.0
        args:
          - --provider=anthropic       # or openai
          - --model=claude-sonnet-4-20250514
          - --prompt-file=.ai/prompts/precommit_gate.md
          - --strict=error             # or warn (continue on LLM failure)

Requires ANTHROPIC_API_KEY or OPENAI_API_KEY in the environment. Customize the policy prompt to match your project's standards.

Docs: precommit-agentic-check/README.md

GitHub Agentic Workflows

AI-powered workflows authored as markdown with YAML frontmatter, compiled to GitHub Actions via gh aw.

Getting started:

gh extension install github/gh-aw   # or: gh extension upgrade gh-aw
gh aw init                           # initialize a repo for agentic workflows
gh aw compile                        # compile .md sources into .lock.yml

Available workflows:

Workflow	Summary	Install
Agents Doc Sync	Keeps CLAUDE.md and AGENTS.md aligned; opens a PR only when sync changes are needed.	gh aw add-wizard aaronspindler/agentic_workflows/agents-doc-sync

Agents Doc Sync

Detects divergence between CLAUDE.md and AGENTS.md, updates the file missing information, and creates a PR only when edits are made.

• Source: .github/workflows/agents-doc-sync.md
• Triggers: daily schedule + manual (workflow_dispatch)
• Engine: Codex (15-minute timeout)
• Safe outputs: PRs prefixed with [docs], labeled documentation + automation, auto-expire after 3 days

---

Repository Layout

agentics/
├── claude-commands/             # Claude Code slash commands (source of truth)
│   ├── commands/                #   /review, /refine, /suggest, /design, /daily, /ticket
│   ├── shared/                  #   Shared config and templates
│   └── Makefile                 #   deploy, diff, status
├── precommit-agentic-check/     # LLM-backed pre-commit gate (Python package)
│   ├── src/agentic_check/       #   CLI, providers, schema, git input
│   ├── tests/
│   └── .ai/prompts/             #   Policy prompt template
├── .github/
│   ├── workflows/               #   Agentic workflow sources (.md) + compiled (.lock.yml)
│   └── agents/                  #   GitHub Copilot agent dispatcher
├── CLAUDE.md                    # Guidance for Claude Code in this repo
├── AGENTS.md                    # Guidance for agentic coding assistants
└── LICENSE                      # MIT