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 Sounio-lang/sounio --skill sounio-codegen-backendsgit clone --depth 1 https://github.com/Sounio-lang/sounioWrote 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/sounio-lang/sounio/sounio-codegen-backends)<a href="https://agentmods.dev/skills/sounio-lang/sounio/sounio-codegen-backends"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/sounio-codegen-backends/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/sounio-lang/sounio/sounio-codegen-backends"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/sounio-codegen-backends.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 | $0.00055 | $0.00352 |
| Opus 5 | $0.00028 | $0.00176 |
| Sonnet 5 | $0.00011 | $0.00070 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
sounio-codegen-backends 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.
What it actually says
Sounio Codegen + Backends
Overview
Implement and debug lowering/codegen without breaking IR invariants or backend feature-flag boundaries.
Workflow
1) Pick the backend path and feature flags
- Cranelift:
compiler/src/codegen/cranelift.rs(feature:jit) - MIR→Cranelift:
compiler/src/codegen/mir_cranelift.rs - LLVM:
compiler/src/codegen/llvm/(feature:llvm) - GPU:
compiler/src/codegen/gpu/(feature:gpu) - Native backend (ELF/linker):
compiler/src/backend/native/
2) Keep IR invariants explicit
- If you change HLIR/MIR shape, validate passes and analyses that assume SSA form.
- Be conservative around effectful ops when doing backend optimizations.
3) Add targeted tests
- Prefer Rust tests close to the backend (
compiler/src/**/testsandcompiler/tests/). - GPU tests typically require
--features gpu(see.claude/commands/sounio-gpu.md).
References
- Codegen map:
references/codegen-navigation.md - Feature flags:
references/feature-flags.md - Claude command references:
.claude/commands/sounio-gpu.md,.claude/commands/sounio-build.md
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.
- 9d ago First seen · 38 lines · 55 tokens per session scan A b63634aa0762
sounio-codegen-backends is a skill published in the GitHub repository Sounio-lang/sounio (6 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 352 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.
Other skills, from other repositories
vera-language
Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.
edge-python
Write, run, test and package Edge Python programs with the edge CLI. Use when editing .py files in an Edge Python project or when the user asks for Edge Python code.
kverus-run
Run the full Rust-to-Verus pipeline (migrate → spec → fix → eval → semantic audit → postprocess) in one command. Use when converting Rust code to verified Verus code end-to-end.
kverus-semantic-audit
Compare original Rust source folders against migrated Verus code folders, identify executable-code differences that may change runtime semantics, and write per-file audit reports to an output folder. Use when checking whether Rust-to-Verus rewriting preserved executable behavior rather than merely verifying…
kverus-migrate
Convert a Rust target into minimally modified Verus-compatible code using an explicit verification command. Use when migrating a specific file and iterating until the verification command succeeds.
vera-language
Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.