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 formal-verification-epistemicgit 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/formal-verification-epistemic)<a href="https://agentmods.dev/skills/sounio-lang/sounio/formal-verification-epistemic"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/formal-verification-epistemic/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/formal-verification-epistemic"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/formal-verification-epistemic.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 | $0.01074 |
| Opus 5 | $0.00028 | $0.00537 |
| Sonnet 5 | $0.00011 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
formal-verification-epistemic 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Formal Verification of Epistemic Programs
When to use this skill
Use this skill when you need to:
- Prove that a Sounio program’s uncertainty propagation obeys specified bounds
- Verify that confidence updates follow Bayesian coherence
- Ensure provenance chains are tamper‑proof and complete
- Integrate SMT solvers (Z3, cvc5) or proof assistants (Lean, Coq) with the Sounio compiler
- Add refinement‑type constraints that involve epistemic quantities
When NOT to use this skill
- For ordinary type checking (use the existing checker)
- For runtime validation of epistemic values (use the standard library’s runtime checks)
- For performance optimizations unrelated to verification
Inputs required
- Specification of the property to be verified (e.g., “output variance ≤ 0.1”)
- References to formal definitions (probability theory, measure theory, GUM)
- Choice of verification backend (SMT, Lean, custom)
- Expected interaction model (compile‑time proof, runtime proof certificate)
Workflow
-
Understand the existing verification infrastructure
- Read
docs/compiler/REFINEMENT_TYPES.mdandself‑hosted/check/refinement.sio - Examine the SMT‑solver integration (if any) in
self‑hosted/smt/ - Review the epistemic semantics (
docs/epistemic/SEMANTICS.md)
- Read
-
Design the verification extension
- Decide which properties are verifiable (variance bounds, confidence thresholds, provenance acyclicity)
- Choose a verification backend and define the interface
- Determine whether proofs are constructed at compile time or verified at runtime
-
Extend the refinement‑type system
- Add new refinement predicates that refer to epistemic attributes (
variance,confidence,provenance) - Modify the refinement checker to interact with the chosen verification backend
- Add new refinement predicates that refer to epistemic attributes (
-
Implement the verification backend integration
- Write a bridge that translates Sounio epistemic constraints into SMT‑LIB or Lean terms
- Handle proof reconstruction and error reporting
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 · 123 lines · 55 tokens per session scan A ff113b0a870a
formal-verification-epistemic 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 1,074 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.
lean-axiom-provenance
Find out what a Lean 4 project actually rests on, and why. Reports every theorem reaching a sorry anywhere upstream, everything settled by nativedecide rather than the kernel, and the shortest path from any declaration to any axiom with each hop labelled a statement dependency or a proof dependency. Use when the user…
lean-generated-proof-audit
Check whether a machine-generated Lean 4 proof actually proves its theorem. A proof can appear in the environment, pass lake build, and still not have been proved: when elaboration fails Lean admits the declaration carrying sorryAx, which an axiom report cannot tell apart from a sorry somebody typed. Use when auditing…
tla-check
Write and iteratively refine executable TLA+ specs (.tla) and TLC model configs (.cfg) from natural-language system designs; run TLC model checking; summarize pass/fail and counterexamples with explicit assumptions and bounds. Use when asked to design or validate a protocol/state machine, create or edit .tla/.cfg…
tla-proof
Write and iteratively refine TLA+ theorem proofs in .tla modules with TLAPS (tlapm); run proof checks and summarize proved vs failed/omitted obligations with explicit assumptions and trust boundaries. Use when asked to create or fix THEOREM or PROOF blocks, diagnose TLAPS failures, strengthen inductive invariants…