auto-claude

auto-claude is a skill for Claude Code from travisjneuman/.claude. It costs 30 tokens per session (973 once invoked), scanned A, original, MIT.

An autonomous coding framework that uses multiple agents to analyze a codebase, plan a feature, implement it, and run quality checks. It can isolate work in a separate Git worktree, a separate working copy of the repository.

In plain words
What is it for?
Use it for established projects with clear patterns, such as CRUD features, forms, API endpoints, authentication flows, and iterative QA.
Why use it?
It reduces the need to guide every implementation step for well-defined, multi-file tasks while keeping the changes separated for review.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it for established projects with clear patterns, such as CRUD features, forms, API endpoints, authentication flows, and iterative QA.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/travisjneuman/.claude/auto-claude
Install

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.

Any agent
npx skills add travisjneuman/.claude --skill auto-claude
Clone the repo
git clone --depth 1 https://github.com/travisjneuman/.claude

Made for: Claude Code.

Wrote 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.

agentmods badge for auto-claude

README.md
[![agentmods](https://agentmods.dev/badge/skills/travisjneuman/.claude/auto-claude/github.svg)](https://agentmods.dev/skills/travisjneuman/.claude/auto-claude)
Your own site
<a href="https://agentmods.dev/skills/travisjneuman/.claude/auto-claude"><img src="https://agentmods.dev/badge/skills/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.

agentmods 80×15 button for auto-claude

Your own site · 80×15
<a href="https://agentmods.dev/skills/travisjneuman/.claude/auto-claude"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/auto-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 973 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 120
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00973
Opus 5 $0.00015 $0.00487
Sonnet 5 $0.00006 $0.00195
Haiku 4.5 $0.00003 $0.00097

Measured 9d ago against content hash 21dda5d1bf36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 9d 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.

skills/auto-claude/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-Claude: Autonomous Coding Framework

Autonomous multi-agent system for complex feature implementation with QA validation.

When to Use

Use Auto-Claude for:

  • Complexity 3-4 - Well-defined features, multiple files
  • Established codebases with clear patterns
  • Repetitive tasks (CRUD, forms, API endpoints, auth flows)
  • When you prefer review-at-end vs step-by-step
  • Features requiring iterative refinement with QA validation

Don't use Auto-Claude for:

  • Complexity 1-2 - Use manual /start-task instead
  • Complexity 5+ - Use /gsd:new-project instead
  • Greenfield projects (no existing codebase patterns)
  • Exploratory/research tasks (unclear requirements)
  • Simple typo fixes or config changes
  • Tasks requiring human decision-making during implementation

Quick Guide:

  • Complexity 1-2 → Manual implementation
  • Complexity 3-4 → Auto-Claude (autonomous)
  • Complexity 5+ → GSD (multi-phase)

Core Capabilities

  1. Codebase Analysis - Generates semantic baseline
  2. Spec Generation - Creates detailed implementation plan
  3. Autonomous Implementation - Multi-agent coordination
  4. Git Worktree Isolation - Safe development in separate worktree
  5. QA Validation - Iterative quality checks
  6. Memory System - Graphiti-powered context retention

Workflow

# From project directory:
/auto-claude Add user authentication with JWT tokens

What Happens:

  1. Analyzes project structure → generates baseline
  2. Creates implementation spec → stores in ~/.auto-claude/specs/
  3. Creates git worktree → isolated development environment
  4. Autonomous agents implement → with QA loops
  5. Returns completed code → ready for review

Output Location: ~/.auto-claude/ (gitignored)

Integration with Existing Workflows

Manual Implementation:

/start-task [description]  → Claude implements step-by-step

Autonomous Implementation:

/auto-claude [description] → Auto-Claude implements autonomously

Read the full file on GitHub · 154 lines

Changes

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.

  1. 9d ago First seen · 154 lines · 30 tokens per session scan A 21dda5d1bf36

Subscribe to this mod's changes

auto-claude is a skill published in the GitHub repository travisjneuman/.claude (97 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 973 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

code-review-loop

Use when opening a PR for review or when receiving review feedback. Activate for keywords like "code review", "PR review", "request review", "review feedback", "address comments", "reviewer said". Covers both ends of the loop: preparing a reviewable PR and acting on feedback rigorously. Always engage with every…

duthaho/claudekit · 79 tokens

release-and-changelog

Use when cutting a release, bumping a version, or writing release notes. Activate for keywords like "release", "version bump", "changelog", "release notes", "tag", "publish", "ship a release", "v1.x", "v2.x". Enforces version hygiene: SemVer respect, changelog discipline, atomic commits, tagged release. Always reflect…

duthaho/claudekit · 99 tokens

git-workflow

Skill "git-workflow" from halflength-ampleness75/claude-code-recipes, covering git workflow, branch naming, rules, conventional commits and format.

halflength-ampleness75/claude-code-recipes · 0 tokens

security-pipeline

Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.

sangrokjung/claude-forge · 48 tokens

caveman-commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…

stevesolun/ctx · 79 tokens

worktree-manager

Create alpha-forge git worktrees with auto branch naming. TRIGGERS - create worktree, new worktree, alpha-forge worktree.

terrylica/cc-skills · 35 tokens