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/neuromechanist/research-skillsWrote 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/neuromechanist/research-skills/project)<a href="https://agentmods.dev/plugins/neuromechanist/research-skills/project"><img src="https://agentmods.dev/badge/plugins/neuromechanist/research-skills/project/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/neuromechanist/research-skills/project"><img src="https://agentmods.dev/badge/plugins/neuromechanist/research-skills/project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
project 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 8d 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": "project",
"version": "0.10.4",
"description": "Complete project lifecycle toolkit: read-only startup preflight, bounded native PR review panels, tracked cross-agent project memory, initialization, cross-agent user-instruction setup, tiered model routing, epic/sprint workflow, onboarding, planning, debugging, engineering loop, agent fan-out, CI/CD, Docker, security, and document processing",
"author": {
"name": "Seyed Yahya Shirazi",
"email": "[email protected]"
},
"license": "BSD-3-Clause",
"commands": "./commands/",
"skills": "./skills/",
"keywords": [
"project",
"init",
"workflow",
"ci-cd",
"docker",
"security",
"scaffolding",
"epic",
"sprint",
"worktree",
"pr-review",
"code-review",
"document-processing",
"onboarding",
"planning",
"debugging",
"fan-out",
"model-routing",
"user-instructions"
]
}
What it installs
The manifest is a name and a version. 16 skills, 5 commands, 3 agents travel with it, and installing the plugin installs all of them — 1,688 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill epic-dev A 84 tokens
- Skill ci-scaffolding A 126 tokens
- Skill implementation-planning A 82 tokens
- Skill init-project A 136 tokens
- Skill workflow-reference A 75 tokens
- Skill codebase-onboarding A 94 tokens
- Skill pr-review-toolkit A 89 tokens
- Skill security-audit A 83 tokens
- Skill docker-packaging A 75 tokens
- Skill project-preflight A 47 tokens
- Skill agent-fanout A 113 tokens
- Skill debugging A 90 tokens
- Skill engineering-loop A 82 tokens
- Skill update-rules A 114 tokens
- Skill document-processing B 94 tokens
- Skill install-user-instructions C 87 tokens
- Command epic-dev A 17 tokens
- Command release-prep A 13 tokens
- Command epic-status A 7 tokens
- Command update-rules A 20 tokens
- Command init-project A 11 tokens
- Agent dependency-auditor A 48 tokens
- Agent release-prep A 55 tokens
- Agent pr-review-toolkit A 46 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.
- 8d ago Changed adcbf1bff1a2
- 10d ago Changed 9aecf5dc04a7
- 1mo ago Changed 180aeeac3d7f
- 1mo ago Changed be6e7e1f0a6e
- 1mo ago First seen · 34 lines scan A be60986b3ddb
project is a plugin published in the GitHub repository neuromechanist/research-skills (49 stars, last pushed yesterday), licensed BSD-3-Clause. 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
pmprompt
Claude plugin for product managers: reusable PM skills (PRDs, roadmaps, prioritization, positioning) for Claude Code and Cowork.
pm-skills
Product manager skill suite for Claude Code — PRD writing, competitor research, daily briefing, HTML prototyping, feature acceptance, UI walkthrough.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.