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 agents/pegasi-ai/reins/openhandsgit clone --depth 1 https://github.com/pegasi-ai/reinsWhat 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 | $0.00000 | $0.00363 |
| Opus 5 | $0.00000 | $0.00181 |
| Sonnet 5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
openhands 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
ToolShield + OpenHands
OpenHands is an open-source AI-driven development platform. ToolShield injects safety guidelines as a microagent that is always loaded into the agent's system prompt.
How It Works
OpenHands supports microagents — specialized markdown files that enhance agents with domain-specific knowledge. ToolShield creates a user-level microagent at ~/.openhands/microagents/toolshield.md with type: repo, which means it is always active (no keyword triggers needed).
Import
toolshield import \
--exp-file postgres-mcp.json \
--agent openhands
You can import multiple tools — each appends to the same microagent file:
toolshield import --exp-file terminal-mcp.json --agent openhands
toolshield import --exp-file filesystem-mcp.json --agent openhands
Unload
toolshield unload --agent openhands
This deletes the toolshield.md microagent file entirely.
File Location
| Platform | Path |
|---|---|
| All | ~/.openhands/microagents/toolshield.md |
Microagent Format
The generated file follows the OpenHands microagent spec:
---
name: toolshield
type: repo
version: 1.0.0
agent: CodeActAgent
---
## Guidelines from Previous Experience
...
Disabling Without Unloading
You can temporarily disable the microagent without deleting it by adding to your OpenHands config.toml:
[agent]
disabled_microagents = ["toolshield"]
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 · 62 lines · 0 tokens per session scan A 73eebe006837
openhands is an agent published in the GitHub repository pegasi-ai/reins (408 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 363 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.
Other agents, from other repositories
implementer
You are the implementer agent in the Polis automated pipeline.
architect
You are the architecture agent in the Polis automated pipeline.
spec-designer
You are the spec-design agent in the Polis automated pipeline.
build_preview
你是一个自主的MCP（Model Context Protocol）源码部署Agent。你的任务是通过自动化流程部署MCP程序从源码：包括阅读文档和代码、安装依赖、启动程序、监控日志以验证启动状态，并使用MCP客户端进行功能验证。请以分步、详细的方式执行以下操作，并在每个阶段报告进度和结果。如果遇到错误，尝试诊断并重试，然后终止流程。.
agent-system
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.
caracal-researcher
Invoke ONLY when explicitly asked for a deep, evidence-based investigation of how Caracal works, where something lives, why it behaves a certain way, or whether a concept/feature exists. This is a Caracal-specific researcher that investigates code, docs, configs, tests, and architecture together to answer with…