forge

forge is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (5,581 once invoked), scanned A, original, MIT.

A development pipeline that takes a product requirements document or feature plan through validation, implementation, testing, auditing, and knowledge capture. TDD, or test-driven development, means writing tests as part of guiding the implementation.

In plain words
What is it for?
Use it to run a full project pipeline from a PRD, or to run it with TDD enforcement and parallel agent work.
Why use it?
It coordinates the stages and quality checks needed to move planned work toward production code, while making handoffs and failures visible.

Command for Claude Code

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/samibs/skillfoundry/forge
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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/commands/samibs/skillfoundry/forge.svg)](https://agentmods.dev/commands/samibs/skillfoundry/forge)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/forge"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/forge.svg" alt="Measured on agentmods" height="20"></a>
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 5,581 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.05581
Opus 5 $0.00000 $0.02790
Sonnet 5 $0.00000 $0.01116
Haiku 4.5 $0.00000 $0.00558

Measured today against content hash 3ef4a55611b3, 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 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- API story: curl the running endpoint, check HTTP status + response body
.claude/commands/forge.md · 554 lines

How it starts

The opening of the file, as written. The whole thing — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge - Summon The Forge

The full pipeline: validate, implement, test, audit, and harvest — all in one command.

Runtime note — two forges, one metaphor. This is the IDE agent-driven /forge: it orchestrates sub-agents through the phases below and gates each handoff with the Anvil (A0–A6). The canonical engine is the CLI sf forge (sf_cli runPipeline), which runs its own fixed, deterministic phase sequence and the CLI quality gates T0–T7. Same metaphor and phase vocabulary, different runtime and gate taxonomy by design. Use this skill inside an AI IDE; use sf forge for a self-contained CLI run.


Usage

/forge                    Full Forge pipeline (semi-auto + parallel)
/forge [prd-file]         Forge a specific PRD
/forge --blitz            Forge with TDD enforcement

Instructions

You are The Forge — 46 rigorous agents forging production code. When /forge is invoked, execute the complete development pipeline from PRD to production-ready code.

When invoked:

Execute these phases in order:

Pre-Flight: Project Readiness

Before Phase 1, run these checks in order:

1. Git repository:

IF NOT a git repository (no .git/ directory):
  AUTO-INITIALIZE:
    git init && git add -A && git commit -m "initial commit"

  OUTPUT:
    ✓ Git repository initialized with initial commit.

2. Execution context (per agents/_execution-context.md): Read or detect .claude/execution-context.json. Display mode:

EXECUTION MODE: REAL | ADVISORY | DEGRADED

In ADVISORY mode, all test and build claims use qualified language throughout the forge run.

3. Stack profile (per agents/_stack-profile.md): Read .claude/stack-profile.json. If missing, detect and write now. All execution agents in Phase 2 use this — never hardcoded commands.

4. Token budget estimate: Count total PRDs and estimate story count. Display before starting:

FORGE ESTIMATE
PRDs found:     [N]
Est. stories:   [N × avg 6]
Est. tokens:    ~[N]k (varies by story complexity)

Proceed? This will run the full pipeline including /feature per story.
Use /forge --yes to skip this prompt.

Read the full file on GitHub · 554 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. today Changed · +22 lines 3ef4a55611b3
  2. yesterday First seen · 532 lines · 0 tokens per session scan A 1c24c951fa23

Subscribe to this mod's changes

forge is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,581 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.