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 agentmods add skills/spiritledsoftware/caplets/installing-capletsnpx skills add spiritledsoftware/caplets --skill installing-capletsgit clone --depth 1 https://github.com/spiritledsoftware/capletsWhat 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 | $0.00056 | $0.01809 |
| Opus 5 | $0.00028 | $0.00905 |
| Sonnet 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 2d 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.
- 2d 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 8d ago), licensed MIT. It adds 56 tokens to every session and 1,809 once invoked, about $0.0003 per session on Opus 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…
create-tutorial
Scaffold a new Membrane API Gateway tutorial in the api-gateway repo — the numbered self-teaching YAML under distribution/tutorials/ /, its support files and README links, and the matching auto-discovered integration test. Use whenever the user asks to create, add, write, or scaffold a tutorial (or a tutorial step)…
optimize-interceptor-docs
Rewrite the reference documentation of a Membrane config element so the page generated at membrane-api.io comes out clean, exact, and reference-style. Use whenever the user wants to write, improve, optimize, polish, or review the docs / Javadoc / @description / @yaml example of an interceptor, plugin, or any…
review-branch
Review the current git branch against master — code quality, refactoring opportunities, regressions, correctness, and test coverage — and print a severity-grouped markdown report. Use whenever the user asks to review the branch, review their changes against master, do a pre-PR / pre-merge review, or asks "is this…
membrane-config
Generate a Membrane API Gateway configuration example or snippet — an apis.yaml (default) or, when explicitly asked, a legacy proxies.xml. Use this whenever the user wants a config, example, or snippet for Membrane: routing a port to a backend, a flow with plugins (setHeader, rateLimiter, basicAuthentication, openapi…
release-notes
Generate GitHub release notes for the Membrane api-gateway repo by collecting the commits between the last release and master, grouping them into Features / Improvements / Fixes / Security / Dependencies, and linking each to its PR. Use whenever the user wants to draft, extract, or write release notes / a changelog /…