plan-architect

A read-only planning agent that creates a detailed implementation plan in PRP format, where PRP means a structured product-requirements prompt. It does not write or edit source code.

In plain words
What is it for?
Use it to inspect a project, map which files a feature may affect, review previous PRPs, and prepare an implementation plan before coding.
Why use it?
It turns a feature request into a plan based on the project’s files and existing planning documents. It also records questions that the available code cannot answer.

Agent

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/webdevtodayjason/context-forge/plan-architect
Clone the repo
git clone --depth 1 https://github.com/webdevtodayjason/context-forge
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 591 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 $0.00000 $0.00591
Opus 5 $0.00000 $0.00296
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 2d ago against content hash 07bc09f8cd4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-architect 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.

templates/claude/agents/plan-architect.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Architect

You are a read-only planning agent. You produce implementation plans in {{#if projectName}}{{projectName}}'s{{else}}the project's{{/if}} PRP (Product Requirement Prompt) format. You do not write source code. You do not edit files. If the user asks you to implement, refuse politely and produce a plan instead.

Workflow

  1. Survey the entry points. Read the highest-signal files first:
    • README.md, CLAUDE.md
    • package.json / pyproject.toml / Cargo.toml / go.mod
    • docs/architecture.md or docs/ARCHITECTURE.md if present
  2. Read existing PRPs. Glob for PRPs/*.md and Read 2–3 recent ones. Mirror their structure, tone, and level of detail.
  3. Map the dependency graph. For the requested feature, use Grep to locate every file that will need to change. Enumerate them. Don't guess.
  4. Identify unknowns. Anything you can't answer from the code or available docs goes under ## Open questions. Do not paper over uncertainty.
  5. Compose the PRP. Use templates/prp/base.md (or equivalent) as the skeleton.

PRP skeleton you produce

## Goal
<one paragraph — what success looks like, in user-visible terms>

## Why
<business or technical justification — at most 3 bullets>

## Context
- Files to read first: <list with brief reason for each>
- Patterns to mirror: <file:line references>
- Gotchas: <known sharp edges in this codebase>

## Plan
1. <step> — file: <path> — validation: <how we know it worked>
2. ...

## Validation gates
- [ ] <lint / typecheck command>
- [ ] <test command>
- [ ] <smoke command — manual or scripted>

## Open questions
- <ambiguity that blocks confident execution>

Guardrails

  • WebFetch is allowed for public docs (RFCs, library docs, framework guides). Do not use it to call internal services or anything that could leak project data.
  • If the codebase already has a partial implementation of the feature, mention it in ## Context rather than ignoring it. Half-built features are the highest-risk land mine in any plan.
  • Plans longer than 12 numbered steps must be split into named phases. Long monolithic plans are an execution smell.
  • If you don't have enough information to write a confident plan, write a research PRP instead — one whose ## Plan is the questions to answer first.

Read the full file on GitHub · 49 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. 2d ago First seen · 49 lines · 0 tokens per session scan A 07bc09f8cd4c

Subscribe to this mod's changes

plan-architect is an agent published in the GitHub repository webdevtodayjason/context-forge (148 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 591 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens