Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Sounio-lang/sounionpx agentmods add skills/sounio-lang/sounio/sounio-pgoWrote 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-pgo)<a href="https://agentmods.dev/skills/sounio-lang/sounio/sounio-pgo"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/sounio-pgo/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-pgo"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/sounio-pgo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01616 |
| Opus 5 | $0.00028 | $0.00808 |
| Sonnet 5 | $0.00011 | $0.00323 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
sounio-pgo 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sounio PGO Pipeline
Overview
The full PGO pipeline: instrument → profile → promote → inline → layout → const_fold → DCE → regalloc → disp8 → compact frame → peephole → codegen.
All passes live in self-hosted/ir/ and self-hosted/native/, wired in self-hosted/compiler/main.sio's compile() function. The native backend is complete as of Sprint 65 (30/30 gate).
Strategies: STANDARD=0, PRECISION=1, AGGRESSIVE=2, INSTRUMENTED=3.
Workflow
1) Understand which pass to touch
| Pass | File | Runs when |
|---|---|---|
| Strategy codegen | ir/lower.sio |
Always — ir_compute_strategy_from_ast() |
| Counter injection | ir/opt_strategy.sio |
strategy=INSTRUMENTED — ir_opt_apply_strategy() |
| .sprof output | native/codegen.sio |
At exit via __prof_dump function |
| Profile reader | ir/profile.sio |
--use-profile flag — sprof_parse() |
| Strategy promotion | ir/profile.sio |
After profile load — sprof_apply_promotion() |
| Inlining | ir/inline.sio |
opts.optimize=true — inl_run_pass() |
| Layout | ir/layout.sio |
opts.optimize + valid profile — layout_sort_by_profile() |
| Const-fold + DCE | ir/opt_cleanup.sio |
opts.optimize=true — opt_cleanup_module() |
| Register alloc (4-preg r12-r15) | native/regalloc.sio |
Always — nc_run_regalloc() (Sprint 52/62) |
| Disp8 adaptive encoding | native/lower_ir.sio |
Always — ir_slot_fits_disp8() (Sprint 63) |
| Compact frame sizing | native/lower_ir.sio |
After regalloc — nc_min_frame_size() (Sprint 64) |
| Peephole optimizer | native/peephole.sio |
After regalloc — ph_run_on_func() (Sprint 65) |
2) Add a new pass
- Create
self-hosted/ir/your_pass.siowithmodule ir::your_passdeclaration - Define main entry:
fn your_pass_run(module: &!IrModule) with Mut, Panic, Div - Add
use ir::your_pass::*inself-hosted/compiler/main.sio - Call
your_pass_run(&!ir_module)after the appropriate stage incompile() - Add self-tests T(N+1) and T(N+2) in
main.sioself-test block
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 · 107 lines · 55 tokens per session scan A a5672f464941
sounio-pgo 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 1,616 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.
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.
migrate-oxfmt
Guide for migrating a project from Prettier or Biome to Oxfmt. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's formatter from Prettier or Biome to Oxfmt.
insta-snapshots
Guide for working with and updating insta snapshot tests in Oxc without terminal interaction.
EMILIA Trust Verification
Verify the authenticity of AI-agent authorization receipts and human-device signoffs. Use this whenever a user shares a "trust receipt", an "authorization receipt", a "signoff", or WebAuthn/passkey approval evidence and asks whether it is valid, genuine, or tampered with. Pairs with the public EMILIA Protocol MCP…
dev-self-merge
Merge self-check for a green PR. Reads the PR's required-check status from the checks API (the committed ci-status feed is RETIRED), outputs MERGE (mark task completed, stand down — server-side auto-enqueue enqueues.