Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/travisjneuman/.claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/travisjneuman/.claude/auto-claude)<a href="https://agentmods.dev/commands/travisjneuman/.claude/auto-claude"><img src="https://agentmods.dev/badge/commands/travisjneuman/.claude/auto-claude/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/travisjneuman/.claude/auto-claude"><img src="https://agentmods.dev/badge/commands/travisjneuman/.claude/auto-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00010 | $0.00432 |
| Opus 5 | $0.00005 | $0.00216 |
| Sonnet 5 | $0.00002 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
auto-claude scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/auto-claude Command
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
Syntax
/auto-claude [feature description]
Examples
/auto-claude Add user authentication with JWT tokens
/auto-claude Implement dark mode toggle with local storage persistence
/auto-claude Refactor API layer to use async/await patterns
What It Does
- Analyzes current project structure
- Generates detailed implementation specification
- Creates isolated git worktree for safe development
- Autonomously implements feature with multi-agent coordination
- Runs QA validation loops until tests pass
- Returns completed implementation for review
Prerequisites
- ✅ Python 3.12+ installed
- ✅
CLAUDE_CODE_OAUTH_TOKENset in~/.auto-claude/.env - ✅ Git repository initialized
- ✅
claude-agent-sdkPython package installed
Output
All analysis, specs, and implementations saved to:
~/.auto-claude/baselines/- Codebase analysis~/.auto-claude/specs/- Feature specifications- Git worktree directory - Actual implementation
Behind the Scenes
Executes:
python ~/.claude/plugins/marketplaces/auto-claude/apps/backend/run.py
With context from current conversation and working directory.
When to Use
Auto-Claude is best for:
- Complex, well-defined features
- Established codebases with clear patterns
- Features requiring multiple files/components
- When you want autonomous implementation
Use /start-task instead for:
- Planning and manual implementation
- Exploratory work
- Simple changes
- When you prefer step-by-step control
Related Commands
/start-task- Manual implementation with planning/gsd:new-project- Multi-phase project managementSkill(generic-code-reviewer)- Code review after completion
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 80 lines · 10 tokens per session scan A 00c2641248d6
auto-claude is a command published in the GitHub repository travisjneuman/.claude (97 stars, last pushed 6d ago), licensed MIT. It adds 10 tokens to every session and 432 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
commit-message
Generate a conventional commit message from staged changes.
pr-description
Generate a PR title and description from the current branch diff against main.
commit-push-pr
An automated Git workflow that checks a project, synchronizes documentation, commits changes, and can create or merge a GitHub pull request. A pull request is a request for teammates to review and add changes to a shared codebase.
update-check.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
versioning
Universal version file discovery and sync. Works with any project structure.
parallel
You are executing the /hydra:parallel command. Start multiple agents simultaneously in different worktrees.