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 agentmods add skills/robcsaszar/ai-forge/ai-forge-updatenpx skills add robcsaszar/ai-forge --skill ai-forge-updategit 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-update)<a href="https://agentmods.dev/skills/robcsaszar/ai-forge/ai-forge-update"><img src="https://agentmods.dev/badge/skills/robcsaszar/ai-forge/ai-forge-update.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 | $0.00105 | $0.02204 |
| Opus 5 | $0.00053 | $0.01102 |
| Sonnet 5 | $0.00021 | $0.00441 |
| Haiku 4.5 | $0.00011 | $0.00220 |
Grade A, and why
ai-forge-update 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 4d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Forge Update
Understand before touching. Confirm before applying. Judge what you've done.
Phase 0 — Load & Recap
Skip condition: If an ai-forge-recap result for the same artifact is already in the conversation context, verify the name matches, skip Phase 0 entirely, and proceed to Phase 1 using that recap.
MANDATORY — Before reading the artifact, load platform constraints:
- For agents: identify the target platform from the file path and extension using the table in
ai-forge-create/references/agents-taxonomy.md, then read that platform's section for frontmatter schema, file naming, line limits, and key constraints. Supported platforms: Claude Code (.claude/agents/*.md), GitHub Copilot (.github/agents/*.agent.md), OpenAI Codex (.codex/agents/*.toml), Google Gemini (.gemini/agents/*.mdor.gemini/skills/*/SKILL.md). - For skills: reference the bundled spec at
ai-forge-judge/references/agentskills-spec.mdfor frontmatter validation.
Porting to another platform? That's a conversion, not an update — it produces a new target-platform file and never writes back to the source path. Run the disposition report first:
node ../ai-forge-create/scripts/validate-metadata.cjs --name "<n>" --description "<d>" \ --target codex --artifact agentApply the PORTABLE and DROPPED rows mechanically. Feed the DECIDE rows — model IDs, tool names, effort enums, anything with no bijective mapping — to
ai-forge-applyas a numbered list so each is an explicit human choice. Never guess one silently; a wrong tool name fails loudly, but a wrong model ID just quietly costs more or reasons worse. Field-level detail is inai-forge-create/references/conversion-guide.md; write the DROPPED and DECIDE rows toMIGRATION-NOTES.mdbeside the ported file.
Identify the target artifact. The user may name it, paste a path, or point to it in context.
What ships with it
1 file 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.
- 4d ago First seen · 195 lines · 105 tokens per session scan A f3e01bcc0c40
ai-forge-update is a skill published in the GitHub repository robcsaszar/ai-forge (0 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 2,204 once invoked, about $0.0005 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.