riper-sigma-core

riper-sigma-core is a cursor rule for coding agents from johnpeterman72/CursorRIPER.agent. It costs 380 tokens per session, scanned A, original, MIT.

A set of rules for moving a coding agent through five modes: read, plan ideas, specify a plan, execute it, and validate the result. It also defines handoffs, memory sections, protection levels, and commands for changing modes.

In plain words
What is it for?
Managing structured coding sessions, recording context and progress, handing work between modes, and controlling whether the agent may read, plan, modify, or review.
Why use it?
It makes the agent's current authority and stage explicit, reducing accidental edits or skipped steps.

Cursor rule

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/johnpeterman72/cursorriper.agent/riper-sigma-core
Clone the repo
git clone --depth 1 https://github.com/johnpeterman72/CursorRIPER.agent
Per session 380 This file is loaded in full into every session.
When invoked 380 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 $0.00380 $0.00380
Opus 5 $0.00190 $0.00190
Sonnet 5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 3d ago against content hash f2dd65f15c99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

riper-sigma-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.

riper-sigma-core.mdc · 40 lines

What it actually says

RIPER·Σ Core Protocol v1.0.3

Modes & Permissions

Ω₁·R: READ-ONLY (Γ₁₋₃,₆) Ω₂·I: IDEATE (no code) Ω₃·P: SPECIFY (exact plans) Ω₄·E: EXECUTE (plan only) Ω₅·V: VALIDATE (no fix)

State Machine

σ₄.Ω_current ∈ [Ω₁..Ω₅] FLOW: Ω₁→Ω₂→Ω₃→Ω₄→Ω₅ ENFORCE: current==agent_mode

Memory Protocol

σ₁: brief | σ₂: patterns | σ₃: tech σ₄: context+STATE | σ₅: progress | σ₆: protection

Handoff Protocol

EXIT: /handoff→σ₄{to:Ω_next,summary} ENTRY: CHECK(σ₄.Ω_current==my_mode)

Protection Levels

Ψ₁-₃: proceed | Ψ₄-₆: caution+confirm

Commands

/r=Ω₁ /i=Ω₂ /p=Ω₃ /e=Ω₄ /rev=Ω₅

Cross-Reference Notation

[↗️σₓ:Rₓ] = Reference to memory file section Γ₁=Files Γ₂=Folders Γ₃=Code Γ₄=Commands Γ₅=Modify Γ₆=Web

Session Protocol

SESSION: @σ₄.Ω_session (maintained across modes) LOCK: σ₄.locked_by (prevent concurrent updates)

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 · 40 lines · 380 tokens per session scan A f2dd65f15c99

Subscribe to this mod's changes

riper-sigma-core is a cursor rule published in the GitHub repository johnpeterman72/CursorRIPER.agent (15 stars, last pushed 1y ago), licensed MIT. It adds 380 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 2026-08-30.