create

A command that turns a ticket number, title, and description into a feature specification. The specification records requirements, acceptance criteria, technical notes, and what is out of scope.

In plain words
What is it for?
Use it to create a spec file for a new feature in the project's configured specifications directory.
Why use it?
It gives a short request enough structure for developers and reviewers to agree on what should be built and how completion will be checked.

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/create
Clone the repo
git clone --depth 1 https://github.com/marcmallet/specforge
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 460 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 $0.00013 $0.00460
Opus 5 $0.00006 $0.00230
Sonnet 5 $0.00003 $0.00092
Haiku 4.5 $0.00001 $0.00046

Measured yesterday against content hash fd87976380bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create 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/create.md · 59 lines

What it actually says

You are helping create a feature spec from a brief description.

The user input is: $ARGUMENTS

The input format is: | |

Parse it like this:

  • Ticket number: the first part e.g. "PROJ-1234"
  • Title: the second part e.g. "Update header navigation"
  • Description: the third part e.g. "We need to update the header navigation background color from white to black"

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's spec is: //spec.md

Create the ticket directory if it does not already exist.

Spec template

Using the parsed description, generate a complete feature spec:

Feature:

Ticket:

Overview

2-3 sentences describing what this feature is and why it exists.

Requirements

  • (list each discrete requirement)

Acceptance Criteria

  • (list each testable condition that proves the feature is done)

Technical Notes

  • (any implementation hints, libraries, patterns to use)

Out of Scope

  • (explicitly list what this feature does NOT cover)

Rules:

  1. Infer reasonable requirements from the description — don't be too literal
  2. Make acceptance criteria testable and specific
  3. Flag anything you assumed with a note like "(assumed)"
  4. Do NOT save the file yet — show the spec to the user first and ask:
    • "Does this look right? Any changes before I save it?"
    • Only save after confirmation
  5. After saving, suggest the next step: "Ready to plan? Run /specforge:plan <ticket-number>"
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 · 59 lines · 13 tokens per session scan A fd87976380bd

Subscribe to this mod's changes

create is a command published in the GitHub repository marcmallet/specforge (9 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 460 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 2026-08-31.