auto

An autonomous workflow mode that repeatedly plans a task, carries it out, and evaluates the result. TDD means test-driven development, where tests guide implementation.

In plain words
What is it for?
It is for tasks that benefit from repeated planning, implementation, testing, and improvement. When connected to its MCP server, it can also track context, dispatch specialist agents, and apply security, accessibility, and performance checklists.
Why use it?
It reduces the need to direct every refinement step manually and stops when quality goals are met or the iteration limit is reached.

Command

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.

agentmods
npx agentmods add commands/jeremydev87/codingbuddy/auto
Clone the repo
git clone --depth 1 https://github.com/JeremyDev87/codingbuddy
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,619 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01619
Opus 5 $0.00000 $0.00809
Sonnet 5 $0.00000 $0.00324
Haiku 4.5 $0.00000 $0.00162

Measured 2d ago against content hash 95816f31a13a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto 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 2d 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.

packages/claude-code-plugin/commands/auto.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AUTO Mode

Purpose

Autonomous PLAN → ACT → EVAL cycle until quality achieved

Mode Availability

Standalone Mode (no MCP server)

This command works without the CodingBuddy MCP server. In standalone mode, you get:

  • Autonomous PLAN → ACT → EVAL iteration
  • Basic agent recommendation per phase
  • TDD workflow guidance
  • Quality-based exit conditions

MCP Enhanced Mode

With the CodingBuddy MCP server connected, you additionally get:

  • parse_mode with full context tracking per phase
  • Specialist agent dispatch for each iteration
  • Contextual checklists (security, accessibility, performance)
  • Cross-session context persistence

Activation

Invoke via /codingbuddy:auto (namespaced) or the AUTO keyword.

Legacy bare /auto is deprecated. See Migration Guide.

This command activates AUTO mode for the CodingBuddy workflow.

Instructions

Important:

  • AUTO mode is an autonomous execution mode that cycles through PLAN → ACT → EVAL automatically
  • User initiates with AUTO keyword and the system handles the entire workflow
  • Continues iterating until quality targets are achieved or maximum iterations reached
  • Best for tasks where iterative refinement is expected

Trigger:

  • Type AUTO to start autonomous execution
  • Korean: 자동
  • Japanese: 自動
  • Chinese: 自动
  • Spanish: AUTOMÁTICO

Purpose: Autonomous iterative development - automatically cycling through planning, implementation, and evaluation until quality standards are met.

How AUTO Works:

  1. Initial Phase: PLAN

    • Creates implementation plan following TDD and augmented coding principles
    • Activates Technical Planner automatically
    • Outputs structured plan with todo items
  2. Execution Phase: ACT

    • Executes the plan created in PLAN phase
    • Follows TDD cycle for core logic, Test-After for UI
    • Maintains quality standards throughout
  3. Evaluation Phase: EVAL

    • Automatically evaluates the implementation (no user prompt required)
    • Activates Code Reviewer Agent
    • Assesses quality across all mandatory perspectives
    • Categorizes issues by severity: Critical, High, Medium, Low

Read the full file on GitHub · 217 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. 2d ago First seen · 217 lines · 0 tokens per session scan A 95816f31a13a

Subscribe to this mod's changes

auto is a command published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,619 tokens. 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 2026-08-30.