000-agentx-core

A set of operating rules for an AI coding agent working in Cursor, a code editor. It points the agent to the project's main instructions and requires a review loop before code or documentation files are changed.

In plain words
What is it for?
Use it to enforce project instruction lookup, structured handoffs, and repeated review steps before and after edits.
Why use it?
It gives the agent a consistent way to find project rules and verify its work. This reduces accidental changes that conflict with the repository's workflow.

Cursor rule for Cursor

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 rules/jnpiyush/agentx/000-agentx-core
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX

Made for: Cursor.

Per session 561 This file is loaded in full into every session.
When invoked 561 The same file — it is already loaded in full.
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 $0.00561 $0.00561
Opus 5 $0.00280 $0.00280
Sonnet 5 $0.00112 $0.00112
Haiku 4.5 $0.00056 $0.00056

Measured 3d ago against content hash ea60230fe60a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

000-agentx-core 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 3d 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.

.cursor/rules/000-agentx-core.mdc · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentX Core Contract (Cursor)

This workspace runs AgentX. Cursor operates in CLI-backed mode: agent definitions, skills, and templates are read in place from the repo. Prefer retrieval-led reasoning -- read the canonical file before generating.

Canonical Sources (read these, do not duplicate)

  • Routing + rules map: AGENTS.md
  • Cross-cutting agent protocol: .github/AGENT-PROTOCOL.md
  • Workflow + handoffs: docs/WORKFLOW.md
  • Skills index (load on demand): Skills.md
  • Agent role contracts: .github/agents/*.agent.md

Quality Loop (NON-SKIPPABLE)

Before editing, creating, or deleting any file for a code or docs change, run .agentx/agentx.ps1 loop start -p "<task>" as the FIRST action. The loop is not done until .agentx/agentx.ps1 loop complete -s "<summary>" succeeds, with at least 5 iterations and a structured reviewer verdict recorded on the final work iteration: loop iterate -s "Subagent Review: <outcome>" -e <evidence> --verdict approved --reviewer <id> --high 0 --medium 0. A summary containing the word "review" no longer satisfies the gate. When the AgentX MCP server is registered (.cursor/mcp.json), use the agentx_loop_* tools instead of typing the CLI -- agentx_loop_iterate accepts the same verdict, reviewer, high and medium fields. The pre-commit hook blocks commits that violate the loop gate.

Workflow Gates

  • Compound Capture, Model Council (ADR/PRD/eval), Execution Plan (>= 8 code files), and Brainstorm gates apply per .github/AGENT-PROTOCOL.md.
  • Scrub before handoff: .agentx/agentx.ps1 scrub -Path <changed-area>.
  • Karpathy guidelines apply to every change.

Conventions

  • Commit format: type: description (#issue) -- feat, fix, docs, test, refactor, perf, chore.
  • ASCII-only: use -> not arrows, - not em-dashes, [PASS]/[FAIL].
  • Create deliverables locally; never push files straight to the remote.

Commands

Role workflows are available as .cursor/commands/*.md, each a thin wrapper over .github/agents/<role>.agent.md. Invoke the matching command, then read that canonical agent file before acting.

Read the full file on GitHub · 53 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. 3d ago First seen · 53 lines · 561 tokens per session scan A ea60230fe60a

Subscribe to this mod's changes

000-agentx-core is a cursor rule published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 6d ago), licensed Apache-2.0. It adds 561 tokens to every session, about $0.0028 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.