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.
npx skills add robcsaszar/ai-forge --skill ai-forge-judgegit clone --depth 1 https://github.com/robcsaszar/ai-forgeWrote 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.
[](https://agentmods.dev/skills/robcsaszar/ai-forge/ai-forge-judge)<a href="https://agentmods.dev/skills/robcsaszar/ai-forge/ai-forge-judge"><img src="https://agentmods.dev/badge/skills/robcsaszar/ai-forge/ai-forge-judge/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.
<a href="https://agentmods.dev/skills/robcsaszar/ai-forge/ai-forge-judge"><img src="https://agentmods.dev/badge/skills/robcsaszar/ai-forge/ai-forge-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.02076 |
| Opus 5 | $0.00038 | $0.01038 |
| Sonnet 5 | $0.00015 | $0.00415 |
| Haiku 4.5 | $0.00008 | $0.00208 |
Grade A, and why
ai-forge-judge 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Forge Judge
Evaluate any LLM-consumed prompt against quality standards, focused on knowledge delta, instruction clarity, and practical usability.
Core Philosophy
Good Prompt = Expert-only Knowledge − What Claude Already Knows
Restating defaults is token waste.
Three Types of Knowledge
| Type | Definition | Treatment |
|---|---|---|
| Expert | Claude genuinely doesn't know this | Must keep — this is the value |
| Activation | Claude knows but may not think of | Keep if brief — serves as reminder |
| Redundant | Claude definitely knows this | Delete — wastes tokens |
Good prompt: >70% Expert, <20% Activation, <10% Redundant.
Evaluation Dimensions
Dimensions are grouped. Universal dimensions always apply. Type-specific modules apply based on what the prompt is. Multiple groups can apply to a single prompt.
Final grade = total score / total applicable points (as %)
| Grade | % | Meaning |
|---|---|---|
| A | 90%+ | Excellent — production-ready |
| B | 80–89% | Good — minor improvements needed |
| C | 70–79% | Adequate — clear improvement path |
| D | 60–69% | Below average — significant issues |
| F | <60% | Poor — needs fundamental redesign |
Group U: Universal (80 pts) — always scored
MANDATORY — READ references/universal-dimensions.md
| ID | Dimension | Pts |
|---|---|---|
| U1 | Knowledge/Instruction Delta | 20 |
| U2 | Mindset + Procedures | 15 |
| U3 | Constraint Quality | 15 |
| U4 | Freedom Calibration | 15 |
| U5 | Practical Usability | 15 |
Group S: Skill Module (40 pts) — SKILL.md targets only
MANDATORY — READ references/skill-dimensions.md
| ID | Dimension | Pts |
|---|---|---|
| S1 | Specification Compliance | 15 |
| S2 | Progressive Disclosure | 15 |
| S3 | Pattern Recognition | 10 |
Group C: Agent / System Prompt Module (40 pts) — agent definitions and system prompts
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agent-dimensions.md 4.6 KB
- references/agentskills-spec.md 3.6 KB
- references/bash-dimensions.md 3.6 KB
- references/extending-groups.md 1.9 KB
- references/failure-patterns.md 5.6 KB
- references/report-template.md 2.0 KB
- references/skill-dimensions.md 8.2 KB
- references/universal-dimensions.md 7.8 KB
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.
- 8d ago First seen · 190 lines · 76 tokens per session scan A 691fc15419f2
ai-forge-judge is a skill published in the GitHub repository robcsaszar/ai-forge (0 stars, last pushed 6d ago), licensed MIT. It adds 76 tokens to every session and 2,076 once invoked, about $0.0004 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.
Other skills, from other repositories
dspy
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.