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-applynpx skills add robcsaszar/ai-forge --skill ai-forge-applygit 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-apply)<a href="https://agentmods.dev/skills/robcsaszar/ai-forge/ai-forge-apply"><img src="https://agentmods.dev/badge/skills/robcsaszar/ai-forge/ai-forge-apply.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 | $0.00109 | $0.01986 |
| Opus 5 | $0.00055 | $0.00993 |
| Sonnet 5 | $0.00022 | $0.00397 |
| Haiku 4.5 | $0.00011 | $0.00199 |
Grade A, and why
ai-forge-apply 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Forge Apply (HITL)
Throw the lasso, pull it tight, move to the next. One change at a time, one approval at a time — no bundling, no skipping ahead.
Core question for every item: What's the smallest change that makes this finding false? Apply only that — nothing more. Verify: if any part of the change were removed, would the finding still be true? If yes, the change is too large.
Workflow
1. Read the list
Parse the numbered improvement list from context. If there are multiple lists or it's unclear which to apply, ask once before starting — not mid-loop. If the response does not resolve the ambiguity, stop: "Still unclear which list to apply — please re-invoke with the target list quoted directly."
If improvements reference specific files, verify they still exist and haven't changed substantially since the evaluation. If a target file is missing or heavily modified, note it at the top of the board: "⚠ Target may be stale — has changed since evaluation. Items may not apply cleanly. (c)ontinue / (Q)uit?"
If ALL items reference stale or missing targets, skip the board entirely: "⚠ All targets stale — re-run the evaluation against the current state rather than forcing through outdated findings." Then stop.
If items have dependencies (item 3 requires item 1), note the dependency at the board level. Do not re-order — apply in sequence and mark dependent items [○] if their prerequisite was skipped.
Check git status before showing the board. If the working directory is not a git repo, note this at the top of the board and skip all commit steps:
ℹ No git repo — changes will be applied but not committed.
Display the full status board upfront: all items with [ ] markers, then (A)pprove all / (s)tart options. Symbols: [ ] pending, [✓] done, [→] in progress, [–] skipped, [○] obsolete.
If the user responds A: apply all items in sequence, then show the final board per step 3.
If the user responds s: begin the per-item loop from item #1.
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 · 149 lines · 109 tokens per session scan A 8d5dcc950261
ai-forge-apply is a skill published in the GitHub repository robcsaszar/ai-forge (0 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 1,986 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.