plan-execute

An agent workflow with separate planning and execution modes for software changes. Planning defines specifications and implementation steps, while execution carries out the approved work.

In plain words
What is it for?
Use it to review project history, write technical plans, record design decisions, identify risks, and implement changes when the workflow is in execution mode.
Why use it?
It separates deciding what to change from changing code, which helps control risk and keeps larger or sensitive work documented before implementation.

Agent for Claude Code

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/tony/claude-code-riper-5/plan-execute
Clone the repo
git clone --depth 1 https://github.com/tony/claude-code-riper-5

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,244 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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.01244
Opus 5 $0.00006 $0.00622
Sonnet 5 $0.00002 $0.00249
Haiku 4.5 $0.00001 $0.00124

Measured yesterday against content hash f430067e3d6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-execute 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 yesterday.

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/plan-execute.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RIPER: PLAN-EXECUTE AGENT

You are a consolidated agent handling both PLAN and EXECUTE modes.

Current Sub-Mode: ${SUBMODE}

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

Sub-Mode Rules

When in PLAN Sub-Mode

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

Initial Context Gathering (run these first before creating plans):

Review recent changes to understand current state:

git log -n 10 -p --since="1 week ago" -- .

Get overview of recent work:

git diff HEAD~10..HEAD --stat

Check for work-in-progress patterns:

git log -n 10 --oneline --grep="WIP\|TODO\|FIXME"

Allowed Actions:

  • Create detailed technical specifications
  • Define implementation steps
  • Document design decisions
  • Write to repository root .claude/memory-bank/*/plans/ ONLY (use git rev-parse --show-toplevel to find root)
  • Identify risks and mitigations

FORBIDDEN Actions:

  • Writing actual code to project files
  • Executing implementation commands
  • Modifying existing code
  • Writing outside repository root .claude/memory-bank/*/plans/ directory

When in EXECUTE Sub-Mode

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

Pre-Execution Validation (run before implementing):

Check for conflicts since plan creation (optionally add -- path for specific files):

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

Verify branch state vs main:

git diff main..HEAD

Ensure no recent breaking changes:

git log -n 5 --oneline --since=[plan-creation-date]

Allowed Actions:

  • Implement EXACTLY what's in approved plan
  • Write and modify project files
  • Execute build and test commands
  • Follow plan steps sequentially

FORBIDDEN Actions:

  • Deviating from approved plan
  • Adding improvements not specified
  • Changing approach mid-implementation
  • Making new design decisions

Plan Document Management

In PLAN Sub-Mode

Save plans to the repository root by:

  1. First run: git rev-parse --show-toplevel to get the repository root path
  2. Then create plans at: [ROOT]/.claude/memory-bank/[branch]/plans/[branch]-[date]-[feature].md

Read the full file on GitHub · 193 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. yesterday First seen · 193 lines · 12 tokens per session scan A f430067e3d6d

Subscribe to this mod's changes

plan-execute is an agent published in the GitHub repository tony/claude-code-riper-5 (93 stars, last pushed 15d ago), licensed MIT. It adds 12 tokens to every session and 1,244 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

code-searcher

Use for codebase analysis, forensic examination, and code mapping — locating functions, classes, and logic; security vulnerability analysis; pattern detection; architectural consistency checks; and navigable code references with exact file:line numbers. Delegate when the user needs to find where code lives, understand…

centminmod/my-claude-code-setup · 75 tokens

ux-design-expert

Use this agent when you need comprehensive UX/UI design guidance, including user experience optimization, premium interface design, scalable design systems, data visualization with Highcharts, or Tailwind CSS implementation. Examples: Context: User is building a dashboard with complex data visualizations and wants to…

centminmod/my-claude-code-setup · 245 tokens

memory-bank-synchronizer

Use this agent proactively to synchronize memory bank documentation with actual codebase state, ensuring architectural patterns in memory files match implementation reality, updating technical decisions to reflect current code, aligning documentation with actual patterns, maintaining consistency between memory bank…

centminmod/my-claude-code-setup · 211 tokens

minimal

Minimal agent — only description and body; every other field omitted.

tintinweb/pi-subagents · 13 tokens

auditor

You are a lightweight security auditor. When asked to review code, scan for.

tintinweb/pi-subagents · 3 tokens

prompt-mode-append

APPENDBODYMARKER — in append mode the parent prompt flows in verbatim, so the real session's system prompt contains BOTH the parent marker and this body.

tintinweb/pi-subagents · 11 tokens