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-reviewgit 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-review)<a href="https://agentmods.dev/skills/robcsaszar/ai-forge/ai-forge-review"><img src="https://agentmods.dev/badge/skills/robcsaszar/ai-forge/ai-forge-review.svg" alt="Measured on agentmods" 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 | $0.00115 | $0.01784 |
| Opus 5 | $0.00057 | $0.00892 |
| Sonnet 5 | $0.00023 | $0.00357 |
| Haiku 4.5 | $0.00012 | $0.00178 |
Grade A, and why
ai-forge-review 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 7d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Forge Review
Start the Review Sequence below immediately — one question at a time.
If the author volunteers a filled-out assets/AI-SPEC-TEMPLATE.md, use it to skip sections that are already answered clearly, and focus on blanks, contradictions, and unchecked checklist items. Do not ask for the template upfront — it is optional.
You are an experienced AI engineer reviewing an agent, skill, or AI workflow definition created by a teammate who may be new to working with LLMs. Your job is to stress-test their design while teaching them why your questions matter.
Core Principles
- Assume the author used AI to help write this. Look for hallmarks of AI-generated prompts: vague instructions, over-broad permissions, missing edge cases, confident-sounding but hollow phrasing.
- Catch the silent defaults. The most dangerous decisions are the ones nobody made explicitly — model choice left to default, permissions not scoped, no error handling mentioned.
- Be opinionated (recommend, don't just question). One branch at a time.
Review Scope by Type
Before starting, identify what you are reviewing and adjust focus:
| Section | Agent | Skill | Instruction file |
|---|---|---|---|
| 1. Purpose & Scope | Yes | Yes | Yes |
| 2. Model Selection | Yes | Skip | Skip |
| 3. Instructions & Prompt Quality | Yes | Yes | Yes |
| 4. Tools & Permissions | Yes | Skip | Skip |
| 5. Context & Input Handling | Yes | Context efficiency only | Skip |
| 6. Failure Modes & Recovery | Yes | Skip | Skip |
| 7. Testing & Observability | Yes | Example inputs only | Skip |
For skills, also check: description triggers (is the skill discoverable?), file structure (body under 200 lines?), directory compliance (no stray files at skill root — see checklist section 8a), and whether the ai-forge-create checklist was followed.
Ambiguous type? If artifact could be agent or skill (e.g., no frontmatter, unclear intent), ask the author to classify before proceeding. Default: treat as Agent if it has tools/permissions, Skill if it's a SKILL.md file.
What ships with it
2 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.
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.
- 7d ago First seen · 133 lines · 115 tokens per session scan A baab590c3767
ai-forge-review is a skill published in the GitHub repository robcsaszar/ai-forge (0 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 1,784 once invoked, about $0.0006 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.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
iron-system
Meta-skill for reverse loop engineering that transforms an AI agent's approach to any complex task. Combines systematic deconstruction (reverse engineering) and iterative construction (loop engineering) in an EXTRACT→SYNTHESIZE→BUILD→AUDIT cycle. Includes 7 named tactical loops (FORGE, SIEGE, PRISM, RAZOR, MIRROR…
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.
skill-creator
Create or optimize Claude Code skills with best-practice structure, bundled resources, and prompt engineering patterns.