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 skills add matteotitta/genesys-skills --skill plugin-scaffoldgit clone --depth 1 https://github.com/matteotitta/genesys-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/skills/matteotitta/genesys-skills/plugin-scaffold)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/plugin-scaffold"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/plugin-scaffold/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/skills/matteotitta/genesys-skills/plugin-scaffold"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/plugin-scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 10 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 44 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What 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 5.1 | $0.00159 | $0.01471 |
| Opus 5.5 | $0.00064 | $0.00588 |
| Sonnet 5.5 | $0.00032 | $0.00294 |
| Haiku 4.5 | $0.00016 | $0.00147 |
Grade A, and why
plugin-scaffold 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plugin-scaffold — Scaffold a plugin bundle
Generates a fresh plugin bundle under projects/apps/genesys-plugins/bundles/{bundle-name}/ following the canonical Claude Code plugin format. Symlinks skills from .claude/skills/ so the bundle stays in sync with canonical sources.
Claude Code triggers
Invoke when user says:
- "scaffold a plugin for [agent/workflow]"
- "create a new bundle"
- "package [agent-name] as a plugin"
- "bundle these skills together:..."
- "new plugin bundle: [name]"
Do NOT invoke when:
- User wants to edit a skill (canonical sources stay in
.claude/skills/— edit there) - User wants to publish a bundle to a public marketplace (that's a separate publish step)
- User is asking about the Claude Code plugin format in general (answer from context, don't scaffold)
Inputs
The skill accepts a bundle spec in one of two forms:
Form 1 — Inline spec
bundle: linkedin-engine
description: "Personal LinkedIn content engine. Voice memo or thought → drafted post on brand in 60s."
agent: social-marketer # defaults to bundle name if omitted
author: genesys-growth
version: "0.1.0"
skills:
- content-skills/linkedin-skills/linkedin-hooks
- content-skills/linkedin-skills/linkedin-expert-posts
- content-skills/linkedin-skills/linkedin-personal-posts
# … add more paths relative to.claude/skills/
commands:
- name: draft-from-thought
description: "Turn a raw thought into a voice-checked LinkedIn post."
- name: weekly-batch
description: "Run the weekly content batch."
cowork_ready: true # false if any skill or MCP is local-only
resale_candidate: true # leave true so a future voice-scrub fork stays on the table
Form 2 — From an existing agent
If the user says "package the social-marketer agent as a plugin", read .claude/agents/{agent-name}.md. The frontmatter already has a skills: list — use it. Prompt the user for bundle name + description only.
Process
- Validate inputs — bundle name kebab-case, all listed skill paths exist under
.claude/skills/, target folder doesn't already exist (else ask to overwrite). - Create folder structure:
projects/apps/genesys-plugins/bundles/{bundle}/ ├──.claude-plugin/plugin.json ├── settings.json ├── README.md ├── agents/{agent}.md (copy + adapt from.claude/agents/{agent}.md) ├── commands/{each}.md ├── skills/ (symlinks to.claude/skills/...) └── examples/ (empty placeholder + README) - Render
plugin.jsonfrom the premium reference using the spec. - Render
settings.jsonwith"agent": "{agent}"as the default. - Copy + adapt the agent definition from
.claude/agents/{agent}.md. Keep the body. Strip theskills:frontmatter (Cowork doesn't read it the same way). Add a short "Bundle context" section referencing the plugin name. - Create symlinks for each skill:
ln -s {absolute-path-to-.claude-skill} skills/{skill-name}. Use absolute paths so symlinks survive bundle moves. - Stub each command under
commands/with a frontmatter + description. Leave the body as a TODO marker for the user to fill with the opinionated chain. - Render
README.mdfrom the premium reference with the bundle name, description, skill list, and install command. - Update the top-level
projects/apps/genesys-plugins/marketplace.jsonto include the new bundle. - Report the created paths and a 1-line install command the user can run to test the bundle locally.
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 · 137 lines · 159 tokens per session scan A 4171dd36c11b
plugin-scaffold is a skill published in the GitHub repository matteotitta/genesys-skills (46 stars, last pushed 11d ago), licensed MIT. It adds 159 tokens to every session and 1,471 once invoked, about $0.0006 per session on Opus 5.5. 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 skills, from other repositories
category-point-of-view
Create a differentiated B2B category point of view that leads with the customer problem, defines the market shift, names the category or strategic frame, and turns it into content, distribution, and measurement guidance.
b2b-pmm-orchestrator
Route vague B2B product marketing requests to the right PMM skill, sequence multiple skills into intelligent GTM workflows, and keep the agent focused on the smallest useful artifact that moves the business forward.
ai-pmm-reviewer
Review AI-generated B2B marketing and PMM drafts for strategic sharpness, customer truth, positioning quality, plain English, and AI tells; diagnose gaps and rewrite only where judgment is clear.
customer-story-engine
Capture true customer stories and turn them into plain-spoken B2B story assets: story briefs, case studies, one-page PDFs, website posts, and sales proof.
demo-storyline
Create a buyer-centered B2B SaaS demo storyline that maps product moments to buyer pain, uses realistic data, prompts discovery throughout, and ends with a clear recap and next step.
sales-narrative-deck
Create a sales-ready B2B narrative deck outline that starts with buyer pain, teaches the market, shows the solution, supports a demo, and gives reps a clear path to proof, pricing, competition, recap, and next steps.