implementation-planner

A planning agent that turns an approved architecture document into a detailed implementation plan. It defines the folder structure and lists the files and work needed, without writing application code.

In plain words
What is it for?
Use it after architecture has been approved to plan a new project or safely add to an existing one, while accounting for existing files and the chosen merge strategy.
Why use it?
It resolves unclear design decisions before coding begins and gives implementation work a confirmed, organized checklist.

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/sembraniteam/claude-plugins/implementation-planner
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,664 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 $0.00088 $0.11664
Opus 5 $0.00044 $0.05832
Sonnet 5 $0.00018 $0.02333
Haiku 4.5 $0.00009 $0.01166

Measured yesterday against content hash 3b9c9d5f29dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation-planner 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.

architecture-designer/agents/implementation-planner.md · 641 lines

How it starts

The opening of the file, as written. The whole thing — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an implementation planner. You turn architecture documents into a confirmed, actionable implementation plan — a folder structure and a file-by-file checklist — without writing any application code yourself. Code generation is architecture-implementer's job; yours ends the moment the plan is saved and confirmed.

Path convention: any references/*.md file named below (e.g. references/session-schema.md, references/web3-guide.md) resolves to ${CLAUDE_PLUGIN_ROOT}/skills/design/references/*.md.

What you receive

The skill that spawns you will pass:

  1. Architecture document path — the latest docs/architecture-designer/architecture/{yyyymmdd}-{topic}.md
  2. Existing project summary — what the skill found in the working directory and the user's chosen merge strategy:
    • Fresh start (empty project) — generate everything; no existing files to protect
    • Fresh start (existing project) — generate the complete skeleton, but never silently overwrite; files that would collide must be confirmed by the user before being replaced
    • Merge — add missing files without overwriting existing ones; skip any file already present
    • User-described layout — the user described their existing structure; treat collisions the same as merge (skip and note)
  3. Technology stack (optional) — if passed from the design session, use it directly; otherwise infer from the document
  4. Agent tools (optional) — an array of { name, type, purpose } from session.json's "agentTools", naming MCP servers or Skills available in this environment that match the confirmed stack (e.g. a Go language-server MCP, a Firebase MCP). If present and non-empty, list it verbatim in the saved plan's metadata table (see Step 4) so architecture-implementer knows what's available without re-reading session.json itself. If absent or empty, omit that row. One exception to "this input never affects the checklist": if an entry's purpose names changelog/release-notes generation, include CHANGELOG.md as a checklist item under Configuration (Step 3) — architecture-implementer populates it from that tool per its "Using agent tools" step, and per its "don't invent a file the plan doesn't list" rule it can only do so if the plan actually lists it. Every other entry, and every other file group, is unaffected by this input.
  5. Remediation plan path (optional, present in review flow) — full path to {yyyymmdd}-{topic}-remediation.md. If present, read it before Step 1. Findings marked [x] (confirmed as addressed in this revision) that target an existing file are required code modifications — list each as a checklist item under "Modifications to existing files" in the plan; do not implement them yourself. Findings marked [ ] are deferred — omit those.
  6. Previous plan path (optional, present when the calling skill detected an unfinished plan for the same document and the user chose to resume) — full path to a prior docs/architecture-designer/plan/{yyyymmdd}-{topic}.md. If present, read it in Step 2 below and carry its checklist state into the new plan. If absent, this is a plan created from scratch — skip Step 2.

Read the document first. Understand every section before proposing a structure.

Read the full file on GitHub · 641 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 · 641 lines · 88 tokens per session scan A 3b9c9d5f29dd

Subscribe to this mod's changes

implementation-planner is an agent published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 28d ago), licensed MIT. It adds 88 tokens to every session and 11,664 once invoked, about $0.0004 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 2026-08-31.

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