006-agentic-workflow

006-agentic-workflow is a cursor rule for Cursor from phuoctrung-ppt/ai-sdlc-workflow. It costs 691 tokens per session, scanned A, original, MIT.

A set of rules for planning, implementing, reviewing, and verifying coding changes through separate planner, worker, and judge roles. It also defines which files and changes require extra review.

In plain words
What is it for?
Use it to classify a change, choose the right implementation workflow, enforce worker file scopes, run proportional verification, and record reviews for protected changes.
Why use it?
It provides an evidence-based process for higher-risk work and prevents protected changes from bypassing planning or review. The rules also define how local checks and durable review records are handled.

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/006-agentic-workflow
Clone the repo
git clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflow

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 006-agentic-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/phuoctrung-ppt/ai-sdlc-workflow/006-agentic-workflow.svg)](https://agentmods.dev/rules/phuoctrung-ppt/ai-sdlc-workflow/006-agentic-workflow)
Your own site
<a href="https://agentmods.dev/rules/phuoctrung-ppt/ai-sdlc-workflow/006-agentic-workflow"><img src="https://agentmods.dev/badge/rules/phuoctrung-ppt/ai-sdlc-workflow/006-agentic-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 691 This file is loaded in full into every session.
When invoked 691 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 $0.00691 $0.00691
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 3d ago against content hash 8d26f0fbd09e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

006-agentic-workflow 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/006-agentic-workflow.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Workflow Guardrails

Canonical workflow: AGENTS.md. Project standards are configured in .cursor/config/workflow-policy.json and always include AGENTS.md.

Execution Order

  1. Classify the change mechanically with .cursor/config/protected-paths.json; do not rely on agent self-report.
  2. Plan with architect-planner for protected module-spanning/high-risk work.
  3. Implement with the narrowest matching worker agent.
  4. Verify locally with checks proportional to risk.
  5. For protected changes, persist docs/reviews/* via judge-agent or /workflow-eval before completion.

Protected Change Classifier

Protected status is shared by plans, judge review, stop hooks, and /workflow-eval:

  • Path globs and keywords live in .cursor/config/protected-paths.json.
  • Multi-file threshold also lives in .cursor/config/protected-paths.json.
  • Fail closed only for protected changes. Fail open for standard changes to avoid team-wide lockouts from broken hooks.
  • /workflow-eval always writes a durable review artifact whenever it runs.

Hook Enforcement

  • preToolUse enforces worker path scopes from .cursor/config/worker-scopes.json.
  • afterFileEdit records edited files for stop-hook classification.
  • stop blocks protected changes without current plan/review artifacts.
  • Stop blocking has a retry cap; after the cap, the hook writes a human escalation artifact instead of looping forever.
  • Manual review override must be explicit and logged with .cursor/hooks/review-override.sh --skip-review "reason".

If scope enforcement blocks a worker, request scope expansion from the orchestrator with the path, reason, and updated acceptance criteria.

Handoff Packet Required

Every worker task should start from a handoff packet containing:

  • Objective
  • In-scope paths
  • Out-of-scope paths
  • Required skills and selected reference files
  • Acceptance criteria
  • Required verification commands
  • Risks or constraints from AGENTS.md

If any field is missing, infer only low-risk details from the codebase. Ask the orchestrator before expanding scope.

Read the full file on GitHub · 70 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 · 70 lines · 691 tokens per session scan A 8d26f0fbd09e

Subscribe to this mod's changes

006-agentic-workflow is a cursor rule published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 17d ago), licensed MIT. It adds 691 tokens to every session, about $0.0035 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.