autocode-new

autocode-new is a command for Claude Code from charles001-wong/autocode-flow. It costs 25 tokens per session (558 once invoked), scanned A, original, MIT.

A setup command that scans a software project and generates a development pipeline tailored to it. The pipeline can include agents, commands, rules, and hooks for stages such as planning, testing, coding, end-to-end checks, and CI/CD.

In plain words
What is it for?
Use it to bootstrap a project-specific automated development process after reviewing the detected language, framework, package manager, tests, linter, and CI/CD setup.
Why use it?
It identifies the project's tools and then uses that information to configure a suitable workflow. It also collects preferences for how each development stage should run.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the autocode-flow plugin — 2 skills, 2 commands, 3 agents, 1 hook shipped together

Good fit Use it to bootstrap a project-specific automated development process after reviewing the detected language, framework, package manager, tests, linter, and CI/CD setup.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add charles001-wong/autocode-flow
Claude Code
/plugin install autocode-flow

Made for: Claude Code.

Or install autocode-flow, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 3 agents, 1 hook.

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 autocode-new

README.md
[![agentmods](https://agentmods.dev/badge/commands/charles001-wong/autocode-flow/autocode-new/github.svg)](https://agentmods.dev/commands/charles001-wong/autocode-flow/autocode-new)
Your own site
<a href="https://agentmods.dev/commands/charles001-wong/autocode-flow/autocode-new"><img src="https://agentmods.dev/badge/commands/charles001-wong/autocode-flow/autocode-new/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 autocode-new

Your own site · 80×15
<a href="https://agentmods.dev/commands/charles001-wong/autocode-flow/autocode-new"><img src="https://agentmods.dev/badge/commands/charles001-wong/autocode-flow/autocode-new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 558 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.
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 $0.00025 $0.00558
Opus 5 $0.00013 $0.00279
Sonnet 5 $0.00005 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured 9d ago against content hash 0afc4f615be6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autocode-new 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.

commands/autocode-new.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/autocode-flow:autocode-new — Generate Project-Specific Dev Pipeline

This command bootstraps a complete autocode development pipeline for the current project through a 3-phase workflow: Scan → Interview → Generate.

Execution Flow

Step 1: Scan the Project

Run the scanner to detect the project's tech stack:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/scan-project.sh" "$(pwd)"

Parse the JSON output and present a summary to the user:

📋 Project Scan Results
━━━━━━━━━━━━━━━━━━━━━━
  Project:    {project_name}
  Language:   {language}
  Framework:  {framework}
  Pkg Mgr:    {package_manager}
  Tests:      {test_framework}
  Linter:     {linter}
  CI/CD:      {ci_cd}
  Docker:     {has_docker}

Ask: "Does this look correct? Any corrections before we proceed?"

Step 2: Interview — Collect Pipeline Preferences

Walk through each stage one at a time. Use the collected scan data to provide smart defaults. For each stage, present the question, wait for an answer, confirm, then move to the next.

Stage order: Plan → TDD → Code → Test → E2E → CI/CD

Read the autocode-interviewer agent at ${CLAUDE_PLUGIN_ROOT}/agents/autocode-interviewer.md for the detailed question set per stage.

Step 3: Generate the autocode System

Read the autocode-generator agent at ${CLAUDE_PLUGIN_ROOT}/agents/autocode-generator.md and follow its workflow.

For each file to generate:

  1. Read the corresponding template from ${CLAUDE_PLUGIN_ROOT}/templates/
  2. Replace {{variables}} with project-specific values
  3. Remove conditional sections that don't apply
  4. Write the file to the correct path in the user's project
  5. If the file already exists, ask user: overwrite / merge / skip

Step 4: Summary

After generation, display:

  1. List of all created files
  2. Available commands: /plan, /tdd, /code, /test, /e2e, /deploy
  3. Suggest: "Try /plan <your next feature> to test the pipeline!"

Important

  • ALWAYS present scan results before interviewing
  • ALWAYS ask ONE stage at a time during the interview
  • ALWAYS confirm the full config before generating
  • NEVER overwrite existing files without asking

Read the full file on GitHub · 73 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 · 73 lines · 25 tokens per session scan A 0afc4f615be6

Subscribe to this mod's changes

autocode-new is a command published in the GitHub repository charles001-wong/autocode-flow (2 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 558 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 2026-08-31.