testing

testing is an agent for coding agents from IvanLi-CN/tavily-hikari. It costs 0 tokens per session (241 once invoked), scanned A, original, MIT.

A backend testing guide that selects the smallest Rust test command or manifest shard able to verify a change. A test shard is one defined portion of a larger test suite.

In plain words
What is it for?
Use it when choosing focused tests, running CI shards, investigating test interference, or validating changes that affect several test groups.
Why use it?
It avoids unnecessarily expensive test runs while preserving required test coverage and reporting when validation cannot run.

Agent

Install

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.

agentmods
npx agentmods add agents/ivanli-cn/tavily-hikari/testing
Clone the repo
git clone --depth 1 https://github.com/IvanLi-CN/tavily-hikari

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 testing

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivanli-cn/tavily-hikari/testing.svg)](https://agentmods.dev/agents/ivanli-cn/tavily-hikari/testing)
Your own site
<a href="https://agentmods.dev/agents/ivanli-cn/tavily-hikari/testing"><img src="https://agentmods.dev/badge/agents/ivanli-cn/tavily-hikari/testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00241
Opus 5 $0.00000 $0.00120
Sonnet 5 $0.00000 $0.00048
Haiku 4.5 $0.00000 $0.00024

Measured 5d ago against content hash 351db5ea8477, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing 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.

docs/agents/testing.md · 18 lines

What it actually says

Backend Test Execution

Use the narrowest command that proves the changed behavior. Run a single Rust target and exact test for a focused change; use scripts/ci_backend_tests.py run-shard --id <shard> when a change crosses one manifest shard.

run-shard and run-all default to low resource limits: two Cargo jobs, one filtered process worker, and two filtered test threads. Use --diagnostic for a fixed 1/1/1 execution when investigating interference. Keep benchmark for measurement; it is not the development default.

Treat run-all, release builds, and Compose checks as heavy targets. Select an execution target explicitly before starting them. If it is unavailable, report the missing validation and wait for the selected target or CI; do not automatically move a heavy command to a different machine.

The backend runner enforces manifest coverage before CI fan-out. Do not bypass it by editing a test command, skipping a shard, or changing a selector to hide an unmatched test. Test upstreams must stay stubbed or sandboxed; production Tavily endpoints require explicit approval.

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. 5d ago First seen · 18 lines · 0 tokens per session scan A 351db5ea8477

Subscribe to this mod's changes

testing is an agent published in the GitHub repository IvanLi-CN/tavily-hikari (347 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 241 tokens. 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.