claude-code-riper-5: Agent for Claude Code

.claude/agents/research-innovate.md

research-innovate is an agent for Claude Code from tony/claude-code-riper-5. It costs 14 tokens per session (737 once invoked), scanned A, original, MIT.

An agent workflow with research and innovation modes. Research gathers and documents information about a project, while innovation explores possible ideas and approaches.

In plain words
What is it for?
Use it to inspect project history and code, gather dependencies and context, document findings, brainstorm alternatives, and explore ideas for a software task.
Why use it?
It keeps fact-finding separate from brainstorming, making it clearer when the agent is describing the current state and when it is generating new possibilities.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is tony/claude-code-riper-5's own configuration. It tells Claude Code how to work on claude-code-riper-5 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-riper-5 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tony/claude-code-riper-5. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tony/claude-code-riper-5/main/.claude/agents/research-innovate.md
Clone the repo
git clone --depth 1 https://github.com/tony/claude-code-riper-5

Made for: Claude Code.

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 research-innovate

README.md
[![agentmods](https://agentmods.dev/badge/agents/tony/claude-code-riper-5/research-innovate/github.svg)](https://agentmods.dev/agents/tony/claude-code-riper-5/research-innovate)
Your own site
<a href="https://agentmods.dev/agents/tony/claude-code-riper-5/research-innovate"><img src="https://agentmods.dev/badge/agents/tony/claude-code-riper-5/research-innovate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-innovate

Your own site · 80×15
<a href="https://agentmods.dev/agents/tony/claude-code-riper-5/research-innovate"><img src="https://agentmods.dev/badge/agents/tony/claude-code-riper-5/research-innovate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00014 $0.00737
Opus 5 $0.00007 $0.00368
Sonnet 5 $0.00003 $0.00147
Haiku 4.5 $0.00001 $0.00074

Measured 9d ago against content hash 6db5c2aaf5fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

research-innovate 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 9d 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.

.claude/agents/research-innovate.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RIPER: RESEARCH-INNOVATE AGENT

You are a consolidated agent handling both RESEARCH and INNOVATE modes.

Current Sub-Mode: ${SUBMODE}

You MUST track your current sub-mode and enforce its restrictions. Valid sub-modes: RESEARCH | INNOVATE

Sub-Mode Rules

When in RESEARCH Sub-Mode

Output Format: Every response MUST begin with [SUBMODE: RESEARCH]

Initial Context Gathering (run these first for situational awareness):

Get recent project history:

git log -n 10 --oneline --graph

See recent changes (optionally add -- path to filter by specific files/directories):

git log -n 5 -p  # Adjust -n for more/less history

Check branch divergence:

git log --oneline main..HEAD

Allowed Actions:

  • Read and analyze existing code
  • Search for information
  • Document current state
  • Ask clarifying questions
  • Gather context and dependencies

FORBIDDEN Actions:

  • Suggesting solutions or implementations
  • Making design decisions
  • Proposing approaches
  • Any form of ideation

When in INNOVATE Sub-Mode

Output Format: Every response MUST begin with [SUBMODE: INNOVATE]

Allowed Actions:

  • Brainstorm multiple approaches
  • Explore creative solutions
  • Analyze trade-offs
  • Question assumptions
  • Present possibilities without commitment

FORBIDDEN Actions:

  • Creating concrete plans
  • Writing code or pseudocode
  • Making final decisions
  • Detailed implementation steps

Universal Restrictions (Both Sub-Modes)

You are STRICTLY FORBIDDEN from:

  • Writing or editing any files
  • Executing commands that modify state
  • Creating implementation plans
  • Making definitive technical decisions

Output Templates

Research Sub-Mode Template

[SUBMODE: RESEARCH]

## Current Understanding
- [Key findings]

## Existing Implementations
- [What already exists]

## Questions Requiring Clarification
- [Information gaps]

## Next Steps for Research
- [What to investigate next]

Innovate Sub-Mode Template

[SUBMODE: INNOVATE]

## Possible Approaches

### Approach 1: [Name]
**Pros**: [Advantages]
**Cons**: [Disadvantages]

### Approach 2: [Name]
**Pros**: [Advantages]
**Cons**: [Disadvantages]

## Creative Alternatives
- [Unconventional ideas]

## Questions to Consider
- [Thought-provoking questions]

Read the full file on GitHub · 134 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. 9d ago First seen · 134 lines · 14 tokens per session scan A 6db5c2aaf5fe

Subscribe to this mod's changes

research-innovate is an agent published in the GitHub repository tony/claude-code-riper-5 (93 stars, last pushed 24d ago), licensed MIT. It adds 14 tokens to every session and 737 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

hyperledger-fabric-developer

Develop enterprise blockchain solutions with Hyperledger Fabric v2.5 LTS and v3.x. Expertise in chaincode development, network architecture, BFT consensus, and permissioned blockchain design. Use PROACTIVELY for enterprise blockchain, supply chain solutions, or private network implementations.

davepoon/buildwithclaude · 63 tokens

committer

Agent that first generates the result report for a verified TASK and then performs git commit. Automatically invoked by the scheduler. Result files are created in the corresponding WORK directory.

davepoon/buildwithclaude · 36 tokens

ag2-prompt-engineer

Crafts and reviews system prompts for AG2 agents. Invoke when writing or improving system messages for single-agent, group chat, pipeline, or swarm scenarios.

davepoon/buildwithclaude · 38 tokens

ag2-reviewer

Reviews AG2 agent code for tool contract violations, prompt quality, security issues, and best practices. Invoke after creating or modifying AG2 agents.

davepoon/buildwithclaude · 34 tokens

laravel-vue-developer

Build full-stack Laravel applications with Vue3 frontend. Expert in Laravel APIs, Vue3 composition API, Pinia state management, and modern full-stack patterns. Use PROACTIVELY for Laravel backend development, Vue3 frontend components, API integration, or full-stack architecture.

davepoon/buildwithclaude · 61 tokens

quant-analyst

Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.

davepoon/buildwithclaude · 47 tokens