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.
git clone --depth 1 https://github.com/jie-worldstatelabs/stagentWrote 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/plugins/jie-worldstatelabs/stagent/stagent)<a href="https://agentmods.dev/plugins/jie-worldstatelabs/stagent/stagent"><img src="https://agentmods.dev/badge/plugins/jie-worldstatelabs/stagent/stagent/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/plugins/jie-worldstatelabs/stagent/stagent"><img src="https://agentmods.dev/badge/plugins/jie-worldstatelabs/stagent/stagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
stagent 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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 3 skills, 9 commands, 1 agent, 8 hooks travel with it, and installing the plugin installs all of them — 380 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill stagent A 54 tokens
- Skill create A 50 tokens
- Skill stagent-setup A 59 tokens
- Command continue A 15 tokens
- Command create A 23 tokens
- Command interrupt A 18 tokens
- Command publish A 10 tokens
- Command start A 18 tokens
- Command login A 8 tokens
- Command whoami A 8 tokens
- Command logout A 10 tokens
- Command cancel C 16 tokens
- Agent workflow-subagent A 91 tokens
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook Notification A not measured
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook SubagentStop A not measured
- Hook UserPromptSubmit A not measured
What ships with it
1 file beside plugin.json 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.
- 1mo ago First seen · 9 lines scan A ac859b977301
stagent is a plugin published in the GitHub repository jie-worldstatelabs/stagent (26 stars, last pushed 5mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
hydraia
A self-contained agentic development harness for Claude Code. One command runs the full feature pipeline: context, think, design + threat model, plan with self-review, sub-agent execution, double code review, and security gates. Bundles every skill and agent it needs.
milestone-driver
Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…
han-research
Pre-planning knowledge-work skills for the Han suite: understanding a problem before anyone commits to a plan. Home of research (research an open-ended question and end at an adversarially-validated recommendation), gap-analysis (compare two artifacts and report what is missing, incomplete, or conflicting), and…
ci-review
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting via gh api.
gemini
Gemini via Antigravity CLI for Claude Code — ask, review, adversarial-review, implement.
council-review
Multi-model code review: your diff reviewed independently by frontier models from multiple AI labs (Anthropic, OpenAI, Google, xAI, and more), synthesized into a verdict-first report — SHIP/NO-SHIP, findings confirmed by 2+ models, single-model dissents attributed. Powered by the Council AI MCP server.