Jolt is a zero-knowledge virtual machine for RISC-V that enables programs to be executed and cryptographically proven. It is for developers and contributors working with zero-knowledge proofs and virtual machines, while the catalogue entries provide instructions and skills for using or developing Jolt.
Borrowing it
Nothing to install: this file belongs to a16z/jolt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/a16z/jolt/main/.claude/skills/new-invariant/SKILL.mdgit clone --depth 1 https://github.com/a16z/joltWrote 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/a16z/jolt/new-invariant)<a href="https://agentmods.dev/skills/a16z/jolt/new-invariant"><img src="https://agentmods.dev/badge/skills/a16z/jolt/new-invariant/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/a16z/jolt/new-invariant"><img src="https://agentmods.dev/badge/skills/a16z/jolt/new-invariant.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 | $0.00013 | $0.01379 |
| Opus 5.5 | $0.00005 | $0.00552 |
| Sonnet 5.5 | $0.00003 | $0.00276 |
| Haiku 4.5 | $0.00001 | $0.00138 |
Grade A, and why
new-invariant 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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill handles all the boilerplate: creating the invariant struct + input type, implementing the Invariant trait, registering it in the JoltInvariants enum, creating a fuzz target (if applicable), and running sync_targets.sh.
<Execution_Policy>
- The user must provide an invariant name (lowercase with underscores, e.g.
sumcheck_binding). - Use the request, spec, and repository context to establish the property and input type; ask only for missing requirements before writing code.
- Follow existing patterns exactly — study the split_eq_bind and soundness invariants as models.
- Always run clippy and the auto-generated tests before reporting success. </Execution_Policy>
Phase 1: Gather Requirements
- Validate the argument
{{ARGUMENTS}}: must be a valid Rust identifier (lowercase alphanumeric + underscores). Reject otherwise. - Gather these requirements from existing context; ask the user only for missing information:
- What property does this invariant check? (becomes the
description()) - What does the input look like? (fields, types, ranges)
- What synthesis targets should it support? (
Test,Fuzz,RedTeam) - Does it need non-trivial setup? (e.g. preprocessing, compilation — default to
Setup = ())
- What property does this invariant check? (becomes the
Phase 2: Explore Context
- Read
jolt-eval/src/invariant/mod.rsto understand the currentJoltInvariantsenum anddispatch!macro. - Read an existing invariant for reference:
- Simple:
jolt-eval/src/invariant/split_eq_bind.rs - Complex (with setup, enrich_input):
jolt-eval/src/invariant/soundness.rs
- Simple:
- Explore the modular crates that own the tested types and APIs.
Phase 3: Implement
Create the invariant file at jolt-eval/src/invariant/<invariant_name>.rs with:
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.
- 1mo ago Changed 5ebc5885b475
- 1mo ago Changed 4722e6b1cf7e
- 2mo ago First seen · 148 lines · 13 tokens per session scan A 472e5730b92b
new-invariant is a skill published in the GitHub repository a16z/jolt (1,059 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 1,379 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
cargo-fuzz
Sets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust projects. Covers cargo fuzz init, the nightly toolchain requirement, fuzztarget! harnesses, Arbitrary-derived structured inputs, sanitizer options, cargo fuzz coverage, and reproducing a crash artifact. Use when fuzzing a Rust crate, writing a…
rust-development
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.
check-impl
Implementation verification - runs format, lint, test, and build checks on the workspace.
mutation-test
Run mutation tests with cargo-mutants to verify test quality. Reports caught, missed, and timed-out mutants.
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.
presentations
Build PowerPoint (PPTX) decks — pptxgenjs when Node is present, python-pptx when not; edit existing decks in place via OOXML — with visual QA before delivery.