forge

forge is a skill for Claude Code, Codex from takubii/smithy. It costs 41 tokens per session (368 once invoked), scanned A, original, MIT.

A research skill that produces a reviewable implementation plan before coding begins. It investigates the codebase and documents the intended files, approach, risks, tasks, and verification checks.

In plain words
What is it for?
Use it to research a software task, compare possible approaches, identify open questions, and prepare an implementation plan for review.
Why use it?
It reduces guesswork by basing the plan on existing code and patterns. The implementation gate keeps source files unchanged until the plan is approved.

Skill for Claude CodeCodex

Part of the smithy plugin — 4 skills shipped together

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 skills/takubii/smithy/forge
Any agent
npx skills add takubii/smithy --skill forge
Clone the repo
git clone --depth 1 https://github.com/takubii/smithy

Made for: Claude Code, Codex.

Or install smithy, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/takubii/smithy/forge.svg)](https://agentmods.dev/skills/takubii/smithy/forge)
Your own site
<a href="https://agentmods.dev/skills/takubii/smithy/forge"><img src="https://agentmods.dev/badge/skills/takubii/smithy/forge.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 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 $0.00041 $0.00368
Opus 5 $0.00020 $0.00184
Sonnet 5 $0.00008 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 4d ago against content hash 3f076b2168ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge 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 4d 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.

claude-code/plugins/smithy/skills/forge/SKILL.md · 75 lines

What it actually says

forge

Produce a reviewable plan before implementation.

Flow

  1. Understand the intent and acceptance criteria.
  2. Research the codebase and collect code facts.
  3. Identify existing patterns and reference implementations.
  4. Draft the approach, target files, alternatives, risks, todos, and verification plan.
  5. Return unresolved product/design questions separately.

Implementation gate

Before the plan is approved:

  • Do not edit tracked source files.
  • Do not start implementation.
  • Return a plan, not a code change.

Research

Record facts, not speculation:

  • Relevant files and why they matter.
  • Existing patterns to follow.
  • APIs, data flow, tests, and constraints.
  • Primary sources: code, docs, issues, or external references when used.

Do not ask the user questions that can be answered from the codebase.

Output format

Return:

## Research

- <code facts and references>

## Plan

- Intent:
- Acceptance criteria:
- Non-goals:
- Target files:
- Approach:
- Reference implementations:
- Alternatives rejected:
- Risks:

## Todos

- [ ] <granular implementation step>

## Verification

- Commands:
- Expected checks:

## Open questions

- <only questions requiring user judgment>

Escalation

Ask the user only for decisions that affect product behavior, scope, acceptance criteria, risk, or non-goals. For implementation mechanics, follow the codebase unless the choice has user-visible consequences.

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. 4d ago First seen · 75 lines · 41 tokens per session scan A 3f076b2168ae

Subscribe to this mod's changes

forge is a skill published in the GitHub repository takubii/smithy (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 368 once invoked, about $0.0002 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.