automatic-differentiation-advanced

automatic-differentiation-advanced is a skill for Claude Code, Codex from Sounio-lang/sounio. It costs 50 tokens per session (1,181 once invoked), scanned A, original, Apache-2.0.

A set of instructions for extending automatic differentiation, the process of calculating how a program’s output changes when its inputs change. It covers higher-order derivatives, control flow, and GPU or distributed computation.

In plain words
What is it for?
Use it when adding second derivatives, Hessians, Jacobians, differentiation through loops or conditionals, GPU gradient computation, or new automatic-differentiation techniques.
Why use it?
It clarifies what information is needed before changing the existing differentiation system, such as mathematical definitions, integration points, and expected resource use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when adding second derivatives, Hessians, Jacobians, differentiation through loops or conditionals, GPU gradient computation, or new automatic-differentiation techniques.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sounio-lang/sounio/automatic-differentiation-advanced
Install

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.

Any agent
npx skills add Sounio-lang/sounio --skill automatic-differentiation-advanced
Clone the repo
git clone --depth 1 https://github.com/Sounio-lang/sounio

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for automatic-differentiation-advanced

README.md
[![agentmods](https://agentmods.dev/badge/skills/sounio-lang/sounio/automatic-differentiation-advanced/github.svg)](https://agentmods.dev/skills/sounio-lang/sounio/automatic-differentiation-advanced)
Your own site
<a href="https://agentmods.dev/skills/sounio-lang/sounio/automatic-differentiation-advanced"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/automatic-differentiation-advanced/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.

agentmods 80×15 button for automatic-differentiation-advanced

Your own site · 80×15
<a href="https://agentmods.dev/skills/sounio-lang/sounio/automatic-differentiation-advanced"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/automatic-differentiation-advanced.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01181
Opus 5 $0.00025 $0.00590
Sonnet 5 $0.00010 $0.00236
Haiku 4.5 $0.00005 $0.00118

Measured 9d ago against content hash 1af7e4cf5d58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

automatic-differentiation-advanced 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.

.roo/skills/automatic-differentiation-advanced/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced Automatic Differentiation

When to use this skill

Use this skill when you need to:

  • Add support for higher‑order derivatives (second‑order, Hessians, Jacobians)
  • Enable differentiation through loops, conditionals, and recursion
  • Optimize gradient computation for GPU or distributed execution
  • Integrate with existing neural‑network libraries (QNN, ONN, SNN)
  • Implement novel AD techniques (checkpointing, source‑to‑source transformation)

When NOT to use this skill

  • For simple forward‑mode AD that already works (use the existing autodiff module)
  • For changes unrelated to differentiation (e.g., adding new math functions)
  • For performance tuning of non‑AD code

Inputs required

  • Specification of the AD extension (which order, which differentiation mode)
  • Mathematical definitions of the new derivative operators
  • Expected performance characteristics and memory usage
  • Integration points with the existing AD infrastructure

Workflow

  1. Understand the current AD implementation

    • Read stdlib/autodiff/ and self‑hosted/check/autodiff.sio (if present)
    • Review the AD test suite under tests/autodiff/
    • Examine the intermediate representation used for gradient computation
  2. Design the extension

    • Decide whether to extend forward‑mode, reverse‑mode, or both
    • Determine how higher‑order derivatives will be represented (nested tangents, Hessian matrices)
    • Plan for control‑flow differentiation (e.g., taping loops, unrolling)
    • Consider memory/performance trade‑offs
  3. Implement the core differentiation logic

    • Add new AD operators to the appropriate standard library modules
    • Extend the compiler's AD lowering passes if necessary
    • Ensure correctness for edge cases (discontinuities, non‑differentiable points)
  4. Integrate with GPU and parallel execution

    • If targeting GPU, modify the GPU backend to support AD primitives
    • Add parallel gradient accumulation for distributed settings
  5. Write tests

    • Add unit tests for each new differentiation operator
    • Include numerical correctness tests against finite‑difference approximations
    • Test differentiation through control‑flow constructs

Read the full file on GitHub · 131 lines

Changes

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.

  1. 9d ago First seen · 131 lines · 50 tokens per session scan A 1af7e4cf5d58

Subscribe to this mod's changes

automatic-differentiation-advanced is a skill published in the GitHub repository Sounio-lang/sounio (6 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,181 once invoked, about $0.0003 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.