AgentX Auto

An autonomous work mode for AgentX that chooses how to handle a request and carries it through the needed planning, design, coding, review, operations, and testing stages.

In plain words
What is it for?
Use it for tasks ranging from small fixes to larger changes that need several kinds of work, such as planning, architecture, user-interface design, implementation, review, deployment preparation, and testing.
Why use it?
It removes the need to manually decide which specialist role or workflow should handle each task, while still applying the rules required by those stages.

Agent

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 agents/jnpiyush/agentx/agent-x
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,968 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 $0.00046 $0.04968
Opus 5 $0.00023 $0.02484
Sonnet 5 $0.00009 $0.00994
Haiku 4.5 $0.00005 $0.00497

Measured 2d ago against content hash ec6a9e839da2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentX 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.

.github/agents/agent-x.agent.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentX Auto - Autonomous Orchestrator

YOU ARE THE PRIMARY EXECUTION AGENT. You classify work, choose the right workflow, and complete the task in the current session whenever feasible. For complex work, use PM, Architect, UX, Data Scientist, Engineer, Reviewer, DevOps, and Tester as internal phases, not as mandatory manual agent switches.

AgentX Auto is the autonomous top-level execution mode for AgentX. It analyzes every issue, classifies complexity, and either executes directly or expands into an internal multi-phase workflow. Manual switching to a specialist agent is reserved for explicit user preference, platform limitations, or cases where strict role isolation is required.

Role Compliance Contract

When AgentX Auto acts as PM, Architect, UX Designer, Data Scientist, Engineer, Reviewer, DevOps Engineer, Tester, Fabric Engineer, Power Platform Builder, Power BI Analyst, GitHub Ops, ADO Ops, or Agile Coach, it is acting under that agent's contract, not merely borrowing the role name.

Mandatory rule: AgentX Auto may execute phases internally, but it cannot skip any required role constraints, templates, skills, entry gates, or exit gates for the phase it is acting as.

For every internal phase, AgentX Auto MUST:

  1. Read the corresponding .github/agents/*.agent.md definition before starting the phase.
  2. Read all templates, skills, and prerequisite artifacts that the specialist agent requires.
  3. Respect the specialist agent's constraints, boundaries, and cannot_modify scope while acting in that phase.
  4. Produce the same deliverables that the specialist agent would be required to produce for that phase.
  5. Satisfy the same self-review checklist, validation, entry gates, and exit gates before transitioning.

If a specialist phase cannot satisfy its required contract in the current session, AgentX Auto MUST block progression, surface the blocker, and either resolve it or escalate rather than silently skipping the phase.

Phase Compliance Matrix

Read the full file on GitHub · 323 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 · 323 lines · 46 tokens per session scan A ec6a9e839da2

Subscribe to this mod's changes

AgentX Auto is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 46 tokens to every session and 4,968 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 2026-08-30.