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/fazxes/claude-code/new-sdk-appgit clone --depth 1 https://github.com/fazxes/Claude-codeWhat 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 | $0.00009 | $0.01782 |
| Opus 5 | $0.00005 | $0.00891 |
| Sonnet 5 | $0.00002 | $0.00356 |
| Haiku 4.5 | $0.00001 | $0.00178 |
Grade A, and why
new-sdk-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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 177 lines · 9 tokens per session scan A d273539c037e
new-sdk-app is a command published in the GitHub repository fazxes/Claude-code (233 stars, last pushed 5mo ago), with no licence file. It adds 9 tokens to every session and 1,782 once invoked, about $0.0000 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 commands, from other repositories
nimbus-commands
The bun scripts, CLI subcommands, and env-var overrides for developing, testing, building, packaging, and releasing Nimbus. Use when asking how to run a script, which coverage gate covers a subsystem, what env var overrides the LLM model, before a bun add (the dependency-safety pre-flight), or when wiring CI gates /…
nimbus-egress
S1 "Local Brain" — the Egress Ledger & nimbus prove. The always-on, append-only, BLAKE3-chained ledger of every authorized outbound action (invariant I29 / static D22): one egressledger row is appended from engine/executor.ts ToolExecutor.gate() BEFORE connectors.dispatch — a denied gate writes a…
nimbus-file-map
Pointer index from "where does X live?" to file path, for the Nimbus monorepo. Use when the user asks where a subsystem, HITL gate, vault key, migration, Tauri allowlist, agent, connector, or RPC handler lives — or when about to grep for an entry-point. Faster than Glob for high-traffic files. Curated by hand and lags…
nimbus-ipc
Complete reference for the Nimbus Gateway IPC layer: JSON-RPC 2.0 conventions, all method namespaces, notification + streaming patterns, the Tauri allowlist, error codes, and the checklist for adding a new method. Use when adding an IPC method, designing a notification, wiring an IPC call from CLI/UI, choosing a…
nimbus-agent-patterns
Authoring built-in Nimbus agents (catchup, expert, impact, ghost, conflicts, huddle, janitor, preflight, why, glossary, decisions, ownership, pre-mortem, negotiate): file location, the read-only/HITL-free shape invariant (and pre-mortem's narrowly-bounded exception to it), parallel sub-agent decomposition via…
nimbus-http-write-surface
The local HTTP API write surface + the WRITEROUTEALLOWLIST / bearer-auth / per-token rate-limit / audit-on-rejection pipeline that protects it (invariant I13). Use when adding/modifying an HTTP POST/PUT/DELETE handler, debating whether a route belongs on the local socket vs the HTTP API, wiring a CI integration that…