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 spiritledsoftware/caplets --skill installing-capletsgit clone --depth 1 https://github.com/spiritledsoftware/capletsWrote 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/spiritledsoftware/caplets/installing-caplets)<a href="https://agentmods.dev/skills/spiritledsoftware/caplets/installing-caplets"><img src="https://agentmods.dev/badge/skills/spiritledsoftware/caplets/installing-caplets/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/spiritledsoftware/caplets/installing-caplets"><img src="https://agentmods.dev/badge/skills/spiritledsoftware/caplets/installing-caplets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 134 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 141 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 | $0.00056 | $0.01809 |
| Opus 5.5 | $0.00022 | $0.00724 |
| Sonnet 5.5 | $0.00011 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
installing-caplets 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 2mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installing Caplets
Bootstrap promise
Run a never-surprise install. Detect first, ask before mutating, show one exact plan, then execute only after the user approves that plan.
This skill may be loaded from a raw GitHub URL. When a troubleshooting branch says to read a reference, fetch the absolute URL shown in that branch.
Immediate read-only probe
Run broad read-only detection immediately. Do not install packages, edit config, start login, or write files in this phase.
Use the relevant safe probes for the current OS and shell:
pwd
uname -a 2>/dev/null || true
command -v node npm pnpm bun npx caplets pi opencode codex claude 2>/dev/null || true
node --version 2>/dev/null || true
npm --version 2>/dev/null || true
pnpm --version 2>/dev/null || true
bun --version 2>/dev/null || true
caplets --version 2>/dev/null || true
caplets doctor --format json 2>/dev/null || caplets doctor 2>/dev/null || true
Also inspect only relevant sections of existing agent config files when present. Look for Caplets entries, MCP server entries, native plugin/package entries, and top-level caplets settings. Redact secrets in summaries. Do not dump full config files into chat.
Completion criterion: you can state whether the Caplets CLI exists, which package managers exist, which agent/client appears active or installed, whether a Caplets config/daemon already exists, and whether the current directory appears project-specific (.caplets/ or project config present).
Ask setup questions
Ask after detection and before mutation. Recommend the detected answer, but let the user choose.
Ask only what is needed:
- Target agent/client. Include detected current agent first. Name first-class targets: Pi, OpenCode, Codex, Claude Code, and generic MCP clients. You may mention popular MCP clients as generic clients when detection suggests them, but do not invent unsupported client IDs.
- Runtime shape. Offer local daemon-first setup and self-hosted remote setup. Hide Caplets Cloud until Cloud is actually available.
- Package manager/install method if
capletsis missing. Detect available package managers, then ask whether to use a global install such asnpm install -g caplets, an equivalent preferred package manager, or temporarynpxuse. - Scope. Default to user/global setup. Ask about project-local setup only when
.caplets/,CAPLETS_PROJECT_CONFIG, or the user’s request indicates repo-specific Caplets. - Remote URL only for self-hosted remote setup. Do not ask for secrets, tokens, passwords, API keys, or credential values in chat.
What ships with it
4 files beside SKILL.md 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.
- 2mo ago First seen · 145 lines · 56 tokens per session scan A ceddeac5e70b
installing-caplets is a skill published in the GitHub repository spiritledsoftware/caplets (14 stars, last pushed 13d ago), licensed MIT. It adds 56 tokens to every session and 1,809 once invoked, about $0.0002 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
aomi-build
Scaffold new Aomi apps and plugins from API docs, OpenAPI/Swagger specs, or SDK references. aomi-build generates production-ready Rust SDK crates (lib.rs, client.rs, tool.rs) with tool schemas, preambles, host-interop flows, and validation — turning a vendor's API surface into AI-agent-callable tools. It covers the…
mcp2cli
Turn any MCP server, OpenAPI spec, or GraphQL endpoint into a CLI. Use this skill when the user wants to interact with an MCP server, OpenAPI/REST API, or GraphQL API via command line, discover available tools/endpoints, call API operations, or generate a new skill from an API. Triggers include "mcp2cli", "call this…
api-design
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
ai-agents-development
Build AI agents and knowledge bases for Falcon Foundry apps. TRIGGER when user asks to "create an AI agent", "add a Foundry agent", "build a knowledge base", "give my agent documents", "expose a collection as an agent tool", "expose an API operation to an agent", "put my agent in Charlotte", "expose an agent as a tool…