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 gear-foundation/vara-skills --skill sails-gtestgit clone --depth 1 https://github.com/gear-foundation/vara-skillsWrote 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/gear-foundation/vara-skills/sails-gtest)<a href="https://agentmods.dev/skills/gear-foundation/vara-skills/sails-gtest"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/sails-gtest/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/gear-foundation/vara-skills/sails-gtest"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/sails-gtest.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00049 | $0.00828 |
| Opus 5 | $0.00024 | $0.00414 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
sails-gtest 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sails Gtest
Goal
Run the Sails-first test loop with generated clients and explicit gtest evidence before any live-node smoke step.
Inputs
../../assets/gtest-report-template.md— report format for gtest results../../references/gtest-cheatsheet.md— quick reference for gtest APIs../../references/gtest-patterns.md— common test patterns../../references/sails-cheatsheet.md— Sails patterns and APIs../../references/sails-gtest-and-local-validation.md— full gtest and validation guide../../references/gear-gas-reservations-and-waitlist.md— gas reasoning for tests../../references/scale-binary-decoding-guide.md— decoding raw reply bytes../../references/sails-syscall-mapping.md—Syscall::*API for gas, message, and execution context
Write the result to docs/plans/YYYY-MM-DD-<topic>-gtest.md.
Expected Loop
- Confirm the implementation target is ready for verification.
- Use generated clients or
GtestEnvinstead of hand-built payloads where the workspace supports them. - If the test must go below generated clients, first decide whether the payload or reply bytes are Sails-routed, plain SCALE, or metadata-driven state output; then apply the raw mental model:
send_bytes*returns aMessageId,run_next_blockreturns theBlockRunResult, and the reply evidence lives in the block result. - Pick the right
BlockRunModeand advance blocks explicitly when replies or deferred effects depend on progression. - Use
run_to_blockwhen delayed work or timeout behavior spans multiple blocks. - Assert behavior, replies, events, or accounting in the test result, not just compilation.
- Record failure mode, fix, and passing command output in the gtest note.
- Route to
../sails-local-smoke/SKILL.mdonly after the suite is green.
Common Pitfalls
- Rust 2024 listener lifetime: Under edition 2024 capture rules, chaining generated-client calls into
listen()can fail with "temporary value dropped while borrowed". In Sails 1.0 the service client implementsListenerdirectly, so bind the service client before listening:let client = program.service_name(); let mut events = client.listen().await.unwrap();
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 61 lines · 49 tokens per session scan A 1494ca5d472c
sails-gtest is a skill published in the GitHub repository gear-foundation/vara-skills (17 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 828 once invoked, about $0.0002 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.