A coding agent framework organized into research, idea generation, planning, implementation, and review phases. It also keeps project notes such as requirements, architecture decisions, technology details, progress, and protected areas.

Use it to research a project, plan changes, implement code, review results, and track project context across development.

It gives the agent a shared project record and a clear stage for each kind of work, reducing lost context between tasks.

riper — Agent by nitingupta220

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 agents/nitingupta220/riperflow/riper

Clone the repo

git clone --depth 1 https://github.com/nitingupta220/riperflow

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,008 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01008
Opus 5	$0.00000	$0.00504
Sonnet 5	$0.00000	$0.00202
Haiku 4.5	$0.00000	$0.00101

Measured 2d ago against content hash ff4c17357675, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

riper 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.

test-project/.opencode/agents/riper.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RIPER-for-All - OpenCode Agent

RIPER-for-All - Universal Rules

Version: 1.0.0 | Generated: 2026-03-12

📚 Path Definitions

📂 = "memory-bank/" 📦 = "memory-bank/backups/"

🔖 Reference Map

Modes (Ω)

Ω₁ = 🔍 Research: Gather information and document findings Ω₂ = 💡 Innovate: Explore options and suggest ideas Ω₃ = 📝 Plan: Create specifications and sequence steps Ω₄ = ⚙️ Execute: Implement code according to plan Ω₅ = 🔎 Review: Validate output against requirements

Phases (Π)

Π₁ = 🌱 UNINITIATED: Framework installed but not started Π₂ = 🚧 INITIALIZING: Setup in progress Π₃ = 🏗️ DEVELOPMENT: Main development work Π₄ = 🔧 MAINTENANCE: Long-term support

Memory Files (Σ)

Σ₁ = 📋 projectbrief.md: Requirements, scope, criteria Σ₂ = 🏛️ systemPatterns.md: Architecture, components, decisions Σ₃ = 💻 techContext.md: Stack, environment, dependencies Σ₄ = 🔮 activeContext.md: Focus, changes, next steps Σ₅ = 📊 progress.md: Status, milestones, issues Σ₆ = 🛡️ protection.md: Protected regions, history, approvals

Protection Levels (Ψ)

Ψ₁ = 🔒 PROTECTED: Highest - never modify Ψ₂ = 🛡️ GUARDED: Ask before modifying Ψ₃ = ℹ️ INFO: Context notes Ψ₄ = 🐛 DEBUG: Debugging code Ψ₅ = 🧪 TEST: Testing code Ψ₆ = ⚠️ CRITICAL: Business logic

Ω RIPER Modes

Ω₁ = 🔍 Research → Gather information and document findings ↪ Commands: /research, /r ↪ Permissions: R:✓ C:✗ U:✗ D:✗

Ω₂ = 💡 Innovate → Explore options and suggest ideas ↪ Commands: /innovate, /i ↪ Permissions: R:✓ C:✓ U:✗ D:✗

Ω₃ = 📝 Plan → Create specifications and sequence steps ↪ Commands: /plan, /p ↪ Permissions: R:✓ C:✓ U:✓ D:✗

Ω₄ = ⚙️ Execute → Implement code according to plan ↪ Commands: /execute, /e ↪ Permissions: R:✓ C:✓ U:✓ D:✓

Ω₅ = 🔎 Review → Validate output against requirements ↪ Commands: /review, /r ↪ Permissions: R:✓ C:✗ U:✗ D:✗

ℙ Permission Matrix

ℙ(Ω₁): {R: ✓, C: ✗, U: ✗, D: ✗} ℙ(Ω₂): {R: ✓, C: ✓, U: ✗, D: ✗} ℙ(Ω₃): {R: ✓, C: ✓, U: ✓, D: ✗} ℙ(Ω₄): {R: ✓, C: ✓, U: ✓, D: ✓} ℙ(Ω₅): {R: ✓, C: ✗, U: ✗, D: ✗}

Read the full file on GitHub · 106 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.

2d ago First seen · 106 lines · 0 tokens per session scan A ff4c17357675

Subscribe to this mod's changes

riper is an agent published in the GitHub repository nitingupta220/riperflow (19 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,008 tokens. 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.

Code review Research Testing ai ai-coding claude-code cli cursor riper

riper