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-compiler-mirgit 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-compiler-mir)<a href="https://agentmods.dev/skills/sounio-lang/sounio/sounio-compiler-mir"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/sounio-compiler-mir/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-compiler-mir"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/sounio-compiler-mir.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 | $0.00051 | $0.00320 |
| Opus 5 | $0.00026 | $0.00160 |
| Sonnet 5 | $0.00010 | $0.00064 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
sounio-compiler-mir 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 12d 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 Compiler MIR
Overview
Make safe, SSA-aware performance improvements in MIR without breaking semantics.
Workflow
1) Orient in the MIR stack
- Read
docs/MIR_OPTIMIZATION_STRATEGY.mdfor the intended pass roadmap. - Use
references/mir-navigation.mdto jump to the right module quickly.
2) When editing an existing pass (e.g., CSE)
- Confirm effect/purity assumptions:
- Treat
Call/CallIndirectas effectful unless proven pure. - Treat
Loadas unsafe for CSE without alias info (current CSE is conservative).
- Treat
- Preserve SSA invariants (or mark
preserves_ssa()false and re-establish SSA).
3) When adding a new MIR pass
- Implement the pass under
compiler/src/mir/optimization/. - Export it in
compiler/src/mir/optimization/mod.rs. - Register it in
compiler/src/mir/optimization/pass_manager.rsif it’s in the default pipeline. - Add focused unit tests close to the pass (see existing pass tests).
References
- MIR map + entry points:
references/mir-navigation.md - New-pass checklist:
references/pass-checklist.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.
- 12d ago First seen · 37 lines · 51 tokens per session scan A f7f6a5eb68e0
sounio-compiler-mir is a skill published in the GitHub repository Sounio-lang/sounio (6 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 320 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
rust-check
Run cargo check on the current Rust project to find compile errors.
stack-trace-rust-probe
Internal helper for meta-stack-trace-investigator. Use when a Rust panic or backtrace needs Rust-specific Result/Option checks, cargo test guidance, and patch targets.
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
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.
clickhouse-rust-type-mismatches
Fix ClickHouse query errors in Rust when using clickhouse-rs crate. Use when: (1) "string is not valid utf8" errors - typically FixedString columns need CAST to String, (2) "tag for enum is not valid" errors - typically Option fields receiving non-NULL values, (3) Sum/count aggregations returning Float64 but Rust…
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.