plan

A command that turns a feature specification into a tagged implementation plan. The plan identifies affected files, ordered tasks, and agreements between server-side and client-side code.

In plain words
What is it for?
It helps break a feature into independently testable backend, frontend, and cross-stack tasks, with shared contracts recorded at the end.
Why use it?
It removes the need to work out the implementation steps and shared data details manually from a feature request.

Command

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 commands/marcmallet/specforge/plan
Clone the repo
git clone --depth 1 https://github.com/marcmallet/specforge
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 428 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 $0.00009 $0.00428
Opus 5 $0.00005 $0.00214
Sonnet 5 $0.00002 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured yesterday against content hash 044030a943ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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.

commands/plan.md · 41 lines

What it actually says

You are helping plan implementation of a feature spec.

Specs directory

Read the project config at: @.claude/specforge/config.json

If the file exists, use the value of the specsDir field as the base directory. If the file does not exist, fall back to .claude/specforge/ inside the current project.

The full path for this ticket is: /$ARGUMENTS/

Read the feature spec at: /$ARGUMENTS/spec.md

Plan

Then do the following:

  1. Summarize the feature in 2-3 sentences
  2. Identify all files that will need to be created or modified in the current project
  3. Break the work into ordered tasks as a markdown checklist, each small enough to implement and test independently
  4. Tag every task with one of:
    • [backend] — server side only, no frontend files touched
    • [frontend] — client side only, no backend files touched
    • [both] — spans both backend and frontend (e.g. a template that needs data bindings AND markup)
  5. For any task tagged [both], define the shared contract explicitly:
    • File(s) involved
    • Field names, endpoint paths, data shapes both sides must agree on
  6. Summarise all shared contracts in a ## Shared Contracts section at the bottom of the plan
  7. Flag any ambiguities, missing information, or decisions that need to be made before starting
  8. Estimate complexity: Low / Medium / High and explain why
  9. Save the final plan to /$ARGUMENTS/plan.md

Do not write any code yet. This is planning only.

After saving the plan, suggest the next step: "Ready to implement? Run /specforge:implement $ARGUMENTS"

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 · 41 lines · 9 tokens per session scan A 044030a943ad

Subscribe to this mod's changes

plan is a command published in the GitHub repository marcmallet/specforge (9 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 428 once invoked, about $0.0000 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.