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/testdouble/hanWrote 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/testdouble/han/han-core)<a href="https://agentmods.dev/plugins/testdouble/han/han-core"><img src="https://agentmods.dev/badge/plugins/testdouble/han/han-core/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/testdouble/han/han-core"><img src="https://agentmods.dev/badge/plugins/testdouble/han/han-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
han-core 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.
What it actually says
{
"name": "han-core",
"description": "The shared foundation of the Han suite: the specialist agent roster the other plugins dispatch (adversarial reviewers, analysts, architects, investigators, and the plan synthesizer), the project-discovery skill with its project-scanner agent, and the canonical evidence and YAGNI rule files. The documentation skills live in han-documentation, the pre-planning research skills in han-research, the planning skills in han-planning, and the coding skills in han-coding; each depends on han-core.",
"version": "3.2.0"
}
What it installs
The manifest is a name and a version. 2 skills, 22 agents travel with it, and installing the plugin installs all of them — 3,479 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill pairing A 189 tokens
- Skill project-discovery A 97 tokens
- Agent data-engineer A 216 tokens
- Agent on-call-engineer A 214 tokens
- Agent devops-engineer A 193 tokens
- Agent junior-developer A 191 tokens
- Agent plan-synthesizer A 159 tokens
- Agent user-experience-designer A 180 tokens
- Agent information-architect A 193 tokens
- Agent system-architect A 188 tokens
- Agent edge-case-explorer A 135 tokens
- Agent gap-analyzer A 162 tokens
- Agent test-engineer A 115 tokens
- Agent software-architect A 195 tokens
- Agent adversarial-security-analyst A 148 tokens
- Agent evidence-based-investigator A 85 tokens
- Agent adversarial-validator A 45 tokens
- Agent behavioral-analyst A 151 tokens
- Agent concurrency-analyst A 161 tokens
- Agent risk-analyst A 140 tokens
- Agent structural-analyst A 131 tokens
- Agent codebase-explorer A 75 tokens
- Agent content-auditor A 72 tokens
- Agent project-scanner A 44 tokens
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 Changed b4bc8f21f41e
- 1mo ago First seen · 6 lines scan A e64237ccaa08
han-core is a plugin published in the GitHub repository testdouble/han (304 stars, last pushed today), licensed MIT. 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
fuse-ai-pilot
AI Pilot workflow agents: sniper (code quality), research-expert, explore-codebase, websearch.
alon-skills
Architecture, code review, prompting, and decision-making skills tuned to Alon Baron's engineering style: model-first, failure-path-aware, YAGNI. v3: six skills rewritten for Claude Fable 5.1 as judgment rules, a build-loop workflow that builds TODOWORKFLOW.md rows unattended, a claude plugin eval suite, and (3.1) a t.
The control plane for game-dev agents — close the loop with verified compile, test, and cross-model review across Unity, Godot, Unreal, and S&box. Lifecycle-aware /qq:go routing, structured runtime state in .qq/, 28 /qq: slash commands. Claude Code-first, agent-agnostic via MCP and plain shell / Python scripts.
ottonomous
Four independent, provider-agnostic skills for product specification, code review, spec-driven implementation, and Moss change summaries.
fable-super-audit
Comprehensive, rubric-driven, whole-repository code audit that ends in a prioritized improvement plan with an executive health grade.
jeff
Meet your new sous chef, Jeff: a model-native quality control plane and cooperative workflow protocol for trusted operators and friendly agents, not a security sandbox.