000-core

000-core is a cursor rule for Cursor from phuoctrung-ppt/ai-sdlc-workflow. It costs 383 tokens per session, scanned A, original, MIT.

A shared workflow for coding agents that organizes work into context gathering, planning, implementation, checking, and review. It also controls which project information each agent reads and requires a handoff summary before work begins.

In plain words
What is it for?
Use it to coordinate multi-step coding tasks, limit context to relevant project files, pass clear assignments to workers, and verify that changes meet stated criteria.
Why use it?
It reduces missed instructions, unnecessary file reading, and poorly defined work between agents. It also makes completion evidence and review expectations explicit.

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/phuoctrung-ppt/ai-sdlc-workflow/000-core
Clone the repo
git clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflow

Made for: Cursor.

Per session 383 This file is loaded in full into every session.
When invoked 383 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 $0.00383 $0.00383
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured 3d ago against content hash 01c1934365f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

000-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-core.mdc · 50 lines

What it actually says

Core Rules (Workflow V2)

Execution Order

  1. Classify — run context-builder; obey Context Packet tiers
  2. Plan — architect-planner for protected or multi-module work
  3. Execute — narrowest worker from activation.agents
  4. Verify — checks proportional to risk
  5. Review — judge-agent for protected work or when reviewMode=required

Context Control (mandatory)

Before coding:

python3 .cursor/context/context-builder.py --task "$TASK" --agent <agent> [--paths ...] [--keywords ...]
  • Read tier1 rules + .memory/ files — NOT full AGENTS.md
  • Read tier2 skill SKILL.md entries only (1–2 for low complexity)
  • Read tier3 patterns when listed
  • Load tier4 references ONLY via --expand-ref or when in tier4.references
  • Never bulk-read docs/reviews/, entire references/ folders, or doNotLoad paths

Handoff Packet

Required before worker dispatch: objective, in-scope paths, out-of-scope paths, acceptance criteria, verification commands.

Machine-readable handoffs: .cursor/context/handoffs/*.json

Completion Evidence

  • Modified files match acceptance criteria
  • Lint/type/test/build run or skipped with concrete reason
  • Docs/ADRs updated when behavior or architecture changed
  • Protected changes have plan + review artifacts

Escalation

  • Scope blocked → orchestrator with path, reason, updated acceptance
  • Missing design spec → designer-worker (frontend UI)
  • Architecture gap → architect-planner
  • Security concern → security-worker
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 · 50 lines · 383 tokens per session scan A 01c1934365f5

Subscribe to this mod's changes

000-core is a cursor rule published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 17d ago), licensed MIT. It adds 383 tokens to every session, about $0.0019 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.