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 commands/paiml/rust-mcp-sdk/appgit clone --depth 1 https://github.com/paiml/rust-mcp-sdkWhat 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 | $0.00000 | $0.00635 |
| Opus 5 | $0.00000 | $0.00318 |
| Sonnet 5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
app 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cargo pmcp app
MCP Apps project management.
Usage
cargo pmcp app <SUBCOMMAND>
Description
Scaffold and manage MCP Apps projects with interactive widgets. Create projects, generate ChatGPT-compatible manifests, and build landing pages.
Subcommands
| Subcommand | Description |
|---|---|
new |
Create a new MCP Apps project |
manifest |
Generate ChatGPT-compatible manifest JSON |
landing |
Generate a standalone demo landing page |
build |
Generate both manifest and landing page |
app new
Create a new MCP Apps project with widget scaffolding.
cargo pmcp app new <NAME> [OPTIONS]
Arguments
| Argument | Required | Description |
|---|---|---|
NAME |
Yes | Name of the project |
Options
| Option | Description |
|---|---|
--path <DIR> |
Directory to create project in (defaults to current directory) |
Example
cargo pmcp app new my-widget-app
cd my-widget-app
cargo build
cargo run &
cargo pmcp preview --url http://localhost:3000 --open
app manifest
Generate a ChatGPT-compatible action manifest.
cargo pmcp app manifest --url <URL> [OPTIONS]
Detects the MCP Apps project in the current directory, auto-discovers widgets, and writes manifest.json.
Options
| Option | Default | Description |
|---|---|---|
--url <URL> |
(required) | Server URL |
--logo <URL> |
- | Logo URL (overrides [package.metadata.pmcp].logo) |
--output <DIR> |
dist |
Output directory |
app landing
Generate a standalone demo landing page HTML.
cargo pmcp app landing [OPTIONS]
Options
| Option | Default | Description |
|---|---|---|
--widget <NAME> |
first alphabetically | Widget to showcase |
--output <DIR> |
dist |
Output directory |
app build
Generate both manifest and landing page.
cargo pmcp app build --url <URL> [OPTIONS]
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 · 123 lines · 0 tokens per session scan A e8ab7493bcfb
app is a command published in the GitHub repository paiml/rust-mcp-sdk (53 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 635 tokens. 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 commands, from other repositories
reflection
Systematically analyze recent interactions and improve Claude Code's configuration, commands, and instructions based on observed patterns and issues.
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.
handoff
Package current state for the next agent.
add-skill
Scaffold a new skill with validation, plugin generation, and README update.
amp-register
Register your agent with an external AMP provider for cross-provider messaging.
nyann:sync-team-profiles
Clone/update registered team-profile sources and register valid profiles under a namespace. Respects the per-source sync interval unless --force.