forge

A multi-step coding workflow that takes a project brief through checks, implementation, testing, review, and knowledge collection. It can run the full process or focus on a specific product requirements document.

In plain words
What is it for?
Use it to turn a project brief into code, enforce test-driven development (writing tests before implementation), run quality checks, and review the result.
Why use it?
It brings many development checks into one repeatable command and controls when work moves from one stage to the next.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,351 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 $0.00009 $0.05351
Opus 5 $0.00005 $0.02676
Sonnet 5 $0.00002 $0.01070
Haiku 4.5 $0.00001 $0.00535

Measured 2d ago against content hash b74079279d85, 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 2d 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.

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
.agents/skills/forge/SKILL.md · 538 lines

How it starts

The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.


min_model: opus

/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 · 538 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. 2d ago First seen · 538 lines · 9 tokens per session scan A b74079279d85

Subscribe to this mod's changes

forge is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 5,351 once invoked, about $0.0000 per session on Opus 5. 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 2026-08-30.

Related

Other skills, from other repositories

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

ring:applying-composition-patterns

React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…

LerianStudio/ring · 68 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens