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/faberlens/hardened-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/faberlens/hardened-skills/productivity-hardened-skills)<a href="https://agentmods.dev/plugins/faberlens/hardened-skills/productivity-hardened-skills"><img src="https://agentmods.dev/badge/plugins/faberlens/hardened-skills/productivity-hardened-skills/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/faberlens/hardened-skills/productivity-hardened-skills"><img src="https://agentmods.dev/badge/plugins/faberlens/hardened-skills/productivity-hardened-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
productivity-hardened-skills 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": "productivity-hardened-skills",
"description": "Notes, tasks, calendars, project management, CRM, and knowledge tools.",
"source": "./",
"strict": false,
"skills": [
"./skills/apollo-hardened",
"./skills/apple-notes-hardened",
"./skills/apple-reminders-hardened",
"./skills/bear-notes-hardened",
"./skills/brainz-calendar-hardened",
"./skills/brainz-tasks-hardened",
"./skills/calendar-hardened",
"./skills/confluence-hardened",
"./skills/feishu-bitable-hardened",
"./skills/feishu-calendar-hardened",
"./skills/feishu-evolver-wrapper-hardened",
"./skills/gog-hardened",
"./skills/hubspot-hardened",
"./skills/jira-hardened",
"./skills/learning-hardened",
"./skills/notion-hardened",
"./skills/obsidian-hardened",
"./skills/obsidian-organizer-hardened",
"./skills/qmd-hardened",
"./skills/salesforce-hardened",
"./skills/servicenow-agent-hardened",
"./skills/things-mac-hardened",
"./skills/trello-hardened"
]
}What it installs
The manifest is a name and a version. 21 skills travel with it, and installing the plugin installs all of them — 731 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill salesforce-hardened A 53 tokens
- Skill hubspot-hardened A 26 tokens
- Skill servicenow-agent-hardened A 36 tokens
- Skill notion-hardened A 20 tokens
- Skill bear-notes-hardened A 20 tokens
- Skill confluence-hardened A 29 tokens
- Skill feishu-calendar-hardened A 25 tokens
- Skill brainz-calendar-hardened A 29 tokens
- Skill calendar-hardened A 22 tokens
- Skill feishu-evolver-wrapper-hardened A 61 tokens
- Skill tasks-hardened A 29 tokens
- Skill feishu-bitable-hardened A 22 tokens
- Skill apple-reminders-hardened A 44 tokens
- Skill obsidian-hardened A 25 tokens
- Skill apollo-hardened A 20 tokens
- Skill obsidian-organizer-hardened A 67 tokens
- Skill learning-hardened A 26 tokens
- Skill qmd-hardened A 24 tokens
- Skill gog-hardened A 23 tokens
- Skill jira-hardened A 70 tokens
- Skill apple-notes-hardened A 60 tokens
What ships with it
1 file beside marketplace.json#productivity-hardened-skills 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 · 31 lines scan A d99b34621b7e
productivity-hardened-skills is a plugin published in the GitHub repository faberlens/hardened-skills (25 stars, last pushed 6mo ago), 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 2026-09-03.
Other plugins, from other repositories
ticktick-cli
Agent-native TickTick workflows for Claude Code backed by the ticktick CLI.
calendar-ninja
Your full calendar operations suite. Meeting prep with context from Gmail + Slack + projects, post-meeting debrief capture, deep work time blocking, action item tracking, and follow-up email drafting. Manages your whole day, not just one meeting.
daily-followup-tracker
Daily multi-channel follow-up sweep. Reads the last 24 hours across email, messaging, today's meetings, and the user's task system. Detects open loops the user owes (waiting on user reply) and today's-new commitments the user just made. Drafts the follow-up messages in the user's actual voice and produces a single…
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.