horka-agent-forge

horka-agent-forge is a skill for Claude Code from joey-barbier/ClaudeCode-Plugin. It costs 133 tokens per session (1,640 once invoked), scanned A, original, MIT.

A gated workflow for creating and testing reusable instructions for AI agents. It requires drafting, A/B testing (comparing two versions), scoring, optimization, and final checks.

In plain words
What is it for?
Use it to build and refine AI-agent skills through repeated tests and quality reviews. It first checks that the required skill-creation and evaluation tools are available.
Why use it?
It prevents an agent skill from being accepted just because it looks complete. Required checks expose weak instructions before they are used in production.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the horka-agent-forge plugin — 1 skill shipped together

Good fit Use it to build and refine AI-agent skills through repeated tests and quality reviews. It first checks that the required skill-creation and evaluation tools are available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joey-barbier/claudecode-plugin/horka-agent-forge
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.

Any agent
npx skills add joey-barbier/ClaudeCode-Plugin --skill horka-agent-forge
Clone the repo
git clone --depth 1 https://github.com/joey-barbier/ClaudeCode-Plugin

Made for: Claude Code.

Or install horka-agent-forge, the plugin that ships this one along with the rest of its 1 skill.

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 horka-agent-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-agent-forge/github.svg)](https://agentmods.dev/skills/joey-barbier/claudecode-plugin/horka-agent-forge)
Your own site
<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/horka-agent-forge"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-agent-forge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for horka-agent-forge

Your own site · 80×15
<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/horka-agent-forge"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-agent-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00133 $0.01640
Opus 5 $0.00067 $0.00820
Sonnet 5 $0.00027 $0.00328
Haiku 4.5 $0.00013 $0.00164

Measured 9d ago against content hash 8764dcb9a3f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

horka-agent-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 9d 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.

plugins/horka-agent-forge/skills/horka-agent-forge/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Forge — Production-Grade Skill Creation Pipeline

This is a non-negotiable, gate-enforced methodology for creating AI skills that actually work in production. Every skill goes through 4 mandatory phases with A/B testing between each. No shortcuts. No "it looks good enough". Data-driven quality or nothing.

Prerequisites Check (BLOCKING)

Before ANYTHING else, verify both required skills are available:

1. skill-creator:skill-creator — for drafting and A/B testing
2. horka-skill-eval:horka-skill-evaluate — for scoring and optimization

Check the available skills list in the system prompt. If EITHER skill is missing:

STOP. Do not proceed.

Tell the user:
"Agent Forge requires two mandatory skills that are not currently installed:
- skill-creator:skill-creator (for drafting + A/B testing)
- horka-skill-eval:horka-skill-evaluate (for scoring + optimization)

Install them first, then re-invoke /horka-agent-forge."

This is not a suggestion. This is a hard gate. Do NOT attempt to create skills manually without these tools. The whole point of this methodology is enforced quality — bypassing the tools defeats the purpose.

Phase 1: Draft via skill-creator

Invoke skill-creator:skill-creator with the user's requirements.

skill-creator handles:

  • Intent capture (what, when, output format)
  • Interview for edge cases and dependencies
  • Writing the SKILL.md draft
  • Creating 2-3 test prompts

Let skill-creator drive this phase entirely. Do not override its process.

Gate 1 output: A drafted SKILL.md + test prompts ready for A/B testing.

Example Flow

User: "I need a skill that generates changelog entries from git commits"

  • Phase 1: skill-creator interviews, drafts changelog-generator/SKILL.md + 3 test prompts
  • Phase 2: A/B test — with-skill covers 5/7 assertions vs 2/7 baseline — PASS
  • Phase 3: skill-evaluate — 71/100 — fix description (+8), add error handling (+6) — 85/100 — PASS
  • Phase 4: A/B retest — optimized 6/7 vs draft 5/7, 15% fewer tokens — PASS
  • Phase 5: Report — Ready for production

Read the full file on GitHub · 181 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. 9d ago First seen · 181 lines · 133 tokens per session scan A 8764dcb9a3f0

Subscribe to this mod's changes

horka-agent-forge is a skill published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 2mo ago), licensed MIT. It adds 133 tokens to every session and 1,640 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens