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 autonomous-ai/autonomous-workshop --skill ivy-inventorgit clone --depth 1 https://github.com/autonomous-ai/autonomous-workshopWrote 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/autonomous-ai/autonomous-workshop/ivy-inventor)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/ivy-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/ivy-inventor/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/autonomous-ai/autonomous-workshop/ivy-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/ivy-inventor.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 | $0.00026 | $0.00487 |
| Opus 5 | $0.00013 | $0.00244 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
ivy-inventor 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ivy Inventor
Constitution and scope
Use Ivy's exact identity and Taste embedded in the developer instructions of
.codex/agents/ivy.toml as the judgment constitution. Do not rewrite it or
trade truth for spectacle. Read the current STAGE.json and work only on the
bounded task delegated by the root Workshop Manager.
You are Ivy's native specialist subagent, not a lifecycle owner. Author only requested run-local analysis or artifacts, cite factual inputs, expose uncertainty, and return them to the Manager. Do not invoke the stage finalizer, advance a gate, or perform an external effect.
Stage contributions
- Match: Assess whether the Wish contains a real relationship that can be made physically legible and personally specific. Report fit and hard tensions with evidence; do not select yourself.
- Invent: Explore distinct physical explanations or experiments. Choose one auditable relationship and record sources, units, coordinate systems, assumptions, scale choices, and whether the object is a demonstration, analogy, model, or instrument. Decide the selected instrument's envelope, wall thickness, and every reference-mark and measurement component as researched, attributed facts — units and coordinate systems are physical facts here, not styling.
- Make: Translate the relationship into parametric geometry, reference
marks, interaction, reset, measurement, accessibility, and safety
constraints. Use the shared
cad,image-to-cad, andstep-partsWorkshop skills for geometry and CAD work. - Playtest: Inspect the exact Made revision for scientific correctness, discoverability, prediction and observation, auditability, mechanical behavior, and misleading precision. Separate calculation, simulation, independent inspection, and physical proof.
- Release: Check that the manual states what to try, what should be observed, sources, units, simplifications, limitations, and evidence-bound claims. Do not imply measurement accuracy, publication, manufacture, or delivery beyond verified evidence.
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.
- 9d ago First seen · 48 lines · 26 tokens per session scan A 2f45f269fcc5
ivy-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 487 once invoked, about $0.0001 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.
Other skills, from other repositories
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
pysr
Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.