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 instructions/shafthq/shaft_engine/java-testsgit clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINEWhat 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 | $0.00037 | $0.00037 |
| Opus 5 | $0.00018 | $0.00018 |
| Sonnet 5 | $0.00007 | $0.00007 |
| Haiku 4.5 | $0.00004 | $0.00004 |
Grade A, and why
SHAFT_ENGINE java-tests.instructions.md 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 2d 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.
What it actually says
Follow the canonical Java-test rules.
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.
- 2d ago First seen · 6 lines · 37 tokens per session scan A 9950d03e95fc
SHAFT_ENGINE java-tests.instructions.md is an instructions file published in the GitHub repository ShaftHQ/SHAFT_ENGINE (407 stars, last pushed today), licensed MIT. It adds 37 tokens to every session, 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 instructions, from other repositories
Cobalt CLAUDE.md
Instructions for Auties00/Cobalt, covering cobalt, build, maven modules, architecture and client hierarchy.
imgui-java CLAUDE.md
Instructions for SpaiR/imgui-java: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.
deptrust AGENTS.md
Instructions for clidey/deptrust, covering what this is, commands, architecture, adding an ecosystem and distribution.
EDDI AGENTS.md
Instructions for labsai/EDDI, covering eddi backend — ai agent instructions, 1. project context, ecosystem, key architecture and build & test commands.
Flydb AGENTS.md
Instructions for zzxCoding/Flydb, covering flydb 仓库 agent 指引, 1. 开始工作前, 2. 仓库结构与版本边界, 3. 修改规则 and 4. 构建与验证.