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 agentmods add skills/badc-mpany/lilith-zero/rust-bulletproofnpx skills add BadC-mpany/lilith-zero --skill rust-bulletproofgit clone --depth 1 https://github.com/BadC-mpany/lilith-zeroWrote 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/badc-mpany/lilith-zero/rust-bulletproof)<a href="https://agentmods.dev/skills/badc-mpany/lilith-zero/rust-bulletproof"><img src="https://agentmods.dev/badge/skills/badc-mpany/lilith-zero/rust-bulletproof.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00696 |
| Opus 5 | $0.00014 | $0.00348 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
rust_bulletproof 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Bulletproof: Advanced Verification Strategy
This skill goes beyond standard unit testing to ensure the mathematical correctness and memory safety of Lilith's critical Rust path (lilith-zero/src). It employs fuzzing, property-based testing, and interpreter-based verification.
When to use this skill
- Critical Logic Changes: Modifications to
policy_validator.rs,pattern_matcher.rs, orsecurity.rs. - Parsing/Input Handling: Changes to how external data (YAML, JSON, Byte streams) is ingested.
- Unsafe Code: ANY addition or modification of
unsafeblocks. - Concurrency: Changes involving
Tokio,Mutex, orRwLock.
How to use it
1. The "No-Panic" Policy (Property Testing)
Use proptest to mathematically assert that functions never panic and properties hold for all inputs, not just example cases.
Command:
# Run property tests specifically (usually marked with #[test])
cd lilith-zero; cargo test --package sentinel --test properties
Note: If tests\properties.rs does not exist, ask the user to create a property test for the new feature.
2. Undefined Behavior Check (Miri)
If the code uses unsafe or does complex pointer arithmetic, you MUST run Miri. Miri interprets the code to find memory leaks, data races, and misalignment.
Command:
# Install Miri if missing
rustup component add miri
# Run tests under Miri
cd lilith-zero; cargo miri test
3. Fuzzing Campaign
For parsers and security boundaries, run a short fuzzing campaign to find edge case crashes.
Command:
# Ensure cargo-fuzz is installed
cargo install cargo-fuzz
# Initialize if needed: cargo fuzz init
# Run the relevant target (e.g., policy_parser)
cd lilith-zero; cargo fuzz run policy_parser -- -max_total_time=300 # 5 minutes
4. Mutation Testing (The "Test the Tests" Rule)
Verify that your tests are actually checking the code by introducing random bugs (mutants) and ensuring tests fail.
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.
- 5d ago First seen · 76 lines · 27 tokens per session scan A ec5d27649960
rust_bulletproof is a skill published in the GitHub repository BadC-mpany/lilith-zero (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 696 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
rust-unit-tests
Write, improve, and run Rust unit tests in the warp Rust codebase.
check
Run Rust fmt, clippy, and unit tests. Use after making Rust code changes.
doctest-conventions
Conventions for authoring rustdoc doctests in playwright-rust — the norun annotation, module-level placement, hidden scaffolding lines, and how doctests are exercised in CI vs pre-commit.
rust-development
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.
rust-tests-guidelines
Guidelines for writing Rust tests. Use this when you want to write Rust tests.
write-rust-tests
Write Rust tests to verify correctness of Rust code. Use this when you want to write Rust tests.