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 softspark/ai-toolkit --skill plugin-creatorgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/plugin-creator)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/plugin-creator"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/plugin-creator/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/softspark/ai-toolkit/plugin-creator"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/plugin-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01350 |
| Opus 5.5 | $0.00013 | $0.00540 |
| Sonnet 5.5 | $0.00007 | $0.00270 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
plugin-creator 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Creator
$ARGUMENTS
Create a new experimental opt-in plugin pack following ai-toolkit conventions.
Workflow
- Capture scope -- what domain should the plugin pack own?
- Pick packaging model -- domain pack, policy pack, or hook/observability pack?
- Define manifest -- name, description, version, domain, compatibility, included assets
- Select assets -- agents, skills, rules, hooks, docs, templates
- Add scaffolding -- create
plugin.json,README.md, and optional subdirectories - Validate -- manifest JSON, included asset references, executable hooks, documentation links
Directory Layout
app/plugins/<plugin-name>/
├── plugin.json
├── README.md
├── agents/ # optional
├── skills/ # optional
├── hooks/ # optional
├── rules/ # optional
└── templates/ # optional
Manifest Template
{
"name": "memory-pack",
"description": "Domain plugin pack for persistent cross-session memory.",
"version": "1.0.0",
"domain": "memory",
"type": "plugin-pack",
"status": "experimental",
"requires": {
"ai-toolkit": ">=1.0.0",
"claude-code": ">=1.0.33"
},
"includes": {
"agents": [],
"skills": ["mem-search"],
"rules": [],
"hooks": ["observation-capture.sh", "session-summary.sh"]
},
"hook_events": {
"observation-capture.sh": "PostToolUse",
"session-summary.sh": "Stop"
}
}
The two hooks are files the pack owns, under app/plugins/memory-pack/hooks/.
That is what makes this a pack rather than a bookmark: installing it puts scripts
on disk and entries in the host's hook config that were not there before.
Authoring Rules
- MUST keep packs domain-scoped — "memory-pack", "mobile-pack", not "misc-pack"
- MUST install something the core install does not already provide.
ai-toolkit installlinks every core skill and agent, so a pack whoseincludesnames only core assets installs zero files and is a no-op. Verify before shipping: install core into a throwawayHOME, then install the pack, and confirm the file count changed. Nine packs were removed in v4.20.0 for failing exactly this check. - MUST reference existing toolkit assets rather than forking them — but referencing alone is not a pack. A pack earns its existence through hooks, scripts, or assets of its own; the reference list is context, not content.
- MUST ship a valid
plugin.jsonwithname,description,version,domain,type,status, andincludes - NEVER have a pack silently alter default global install behavior — experimental packs are opt-in only
- NEVER copy an agent or skill file into a pack when referencing the toolkit-level version suffices; duplication creates drift
- CRITICAL: optional hooks bundled in a pack must be executable (
chmod +x) and documented in the pack README with their install semantics - MANDATORY: the pack README names supported runtimes (
claude,codex, orall) and explains that the pack is not part of the default install
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 · 105 lines · 33 tokens per session scan A 3b7836475115
plugin-creator is a skill published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 1,350 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.