aurora-agent: Skill for Claude Code

.agents/skills/verify-crate/SKILL.md

verify-crate is a skill for Claude Code, Codex from AURORA-NEURO/aurora-agent. It costs 76 tokens per session (1,134 once invoked), scanned A, original, Apache-2.0.

A verification guide for a Rust crate in the bioprism workspace. It defines a green result as passing tests and zero Clippy warnings, with Clippy being Rust's code-linting tool.

In plain words
What is it for?
Use it before declaring a crate complete or after agent-made changes, especially when test results or the reported number of tests seem questionable.
Why use it?
It helps distinguish real test failures from environment problems, such as Windows blocking a test program before the test suite runs, and avoids trusting incorrect test counts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is AURORA-NEURO/aurora-agent's own configuration. It tells Claude Code and Codex how to work on aurora-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aurora-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AURORA-NEURO/aurora-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AURORA-NEURO/aurora-agent/main/.agents/skills/verify-crate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AURORA-NEURO/aurora-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for verify-crate

README.md
[![agentmods](https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/verify-crate/github.svg)](https://agentmods.dev/skills/aurora-neuro/aurora-agent/verify-crate)
Your own site
<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/verify-crate"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/verify-crate/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.

agentmods 80×15 button for verify-crate

Your own site · 80×15
<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/verify-crate"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/verify-crate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01134
Opus 5 $0.00038 $0.00567
Sonnet 5 $0.00015 $0.00227
Haiku 4.5 $0.00008 $0.00113

Measured 9d ago against content hash ee7108027e31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-crate 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 9d 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.

.agents/skills/verify-crate/SKILL.md · 107 lines

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.

Verify a crate

Green means both of these, per crate:

cargo test -p bioprism-<crate> --offline
cargo clippy -p bioprism-<crate> --all-targets --offline

Zero failures, zero warnings. --offline is not optional — this workspace builds against pinned versions with no network, and omitting it produces a confusing registry error rather than a build.

Do not trust a reported test count without running it

Agents and humans both miscount. Run the suite yourself and sum the test result lines:

cargo test -p bioprism-<crate> --offline 2>&1 | grep -E "^test result: ok" | awk '{s+=$4} END {print s}'

The failure that is not a failure

Windows Application Control sometimes blocks a freshly linked test binary:

error: test failed, to rerun pass `-p bioprism-<crate> --test <suite>`
Caused by:
  could not execute process ... (never executed)
Caused by:
  An Application Control policy has blocked this file. (os error 4551)

A suite that never ran looks exactly like a suite that failed. Worse, cargo test continues to the next binary, so a naive sum silently under-reports — this has already produced a wrong count once (27 reported where the true figure was 75).

Force a relink to get a new binary hash the policy allows:

touch crates/<crate>/tests/*.rs
cargo test -p bioprism-<crate> --offline

If a per-crate count looks lower than expected, check for never executed before concluding anything about the code.

It bites the workspace sum harder than any single crate

This is the part that keeps costing time. A blocked binary makes cargo test --workspace lose every test after it, silently — the run reports error: test failed, cargo moves on, and the sum you take at the end is short by an amount nothing on screen tells you.

It has now hit five recorded times in this repository:

Where Reported True
workspace, Batch I (3a5bae2) 344 4,327
workspace, fiber batch (0f5b53b) — three binaries blocked short by 66 6,171
crates/fabric (18c5475) 130 176
crates/bioevalx (9a04c8b) — one blocked, three later never ran 113
the original per-crate case in this skill 27 75

Read the full file on GitHub · 107 lines

Changes

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.

  1. 9d ago First seen · 107 lines · 76 tokens per session scan A ee7108027e31

Subscribe to this mod's changes

verify-crate is a skill published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 1,134 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

klever-dev

End-to-end Klever blockchain development — smart contracts (Rust/WASM), transaction building (@klever/connect, klever-go-sdk), deployment via ksc + koperator, and on-chain interaction via MCP tools. Use when the task involves KLV, KDA tokens, klv1 addresses, Klever smart contracts, or Klever node/API interaction.

klever-io/mcp-klever-vm · 76 tokens

qa

QA test a live website with Axon discovery/content evidence plus browser automation when interaction is required. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.

dinglebear-ai/axon · 52 tokens

rust-development

Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.

navikt/copilot · 27 tokens

cargo-fuzz

Use when initializing, running, measuring coverage, or triaging a cargo-fuzz target in a Rust crate. Not for remote, credential, publish, deploy, or irreversible changes.

OutlineDriven/outline-driven-development · 40 tokens

testing-python

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, async testing, and CI integration.

AI-Riksarkivet/ra-mcp · 48 tokens

rust-sota-arsenal

Reference guide for state-of-the-art Rust tooling across refactoring, profiling, benchmarking, testing, and SIMD optimization. Use whenever the.

terrylica/cc-skills · 34 tokens