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.
npx agentmods add agents/jnpiyush/agentx/agent-xgit clone --depth 1 https://github.com/jnPiyush/AgentXWhat 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 | $0.00046 | $0.04968 |
| Opus 5 | $0.00023 | $0.02484 |
| Sonnet 5 | $0.00009 | $0.00994 |
| Haiku 4.5 | $0.00005 | $0.00497 |
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.
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:
- Read the corresponding
.github/agents/*.agent.mddefinition before starting the phase. - Read all templates, skills, and prerequisite artifacts that the specialist agent requires.
- Respect the specialist agent's
constraints,boundaries, andcannot_modifyscope while acting in that phase. - Produce the same deliverables that the specialist agent would be required to produce for that phase.
- 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
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.
- 2d ago First seen · 323 lines · 46 tokens per session scan A ec6a9e839da2
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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.