Borrowing it
Nothing to install: this file belongs to Project-Kiri/Kiri-Friends. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Project-Kiri/Kiri-Friends/main/.agents/skills/kiri-friends-core/SKILL.mdgit clone --depth 1 https://github.com/Project-Kiri/Kiri-FriendsWrote 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/project-kiri/kiri-friends/kiri-friends-core)<a href="https://agentmods.dev/skills/project-kiri/kiri-friends/kiri-friends-core"><img src="https://agentmods.dev/badge/skills/project-kiri/kiri-friends/kiri-friends-core/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/project-kiri/kiri-friends/kiri-friends-core"><img src="https://agentmods.dev/badge/skills/project-kiri/kiri-friends/kiri-friends-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00046 | $0.00549 |
| Opus 5 | $0.00023 | $0.00275 |
| Sonnet 5 | $0.00009 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
kiri-friends-core 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 12d 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.
What it actually says
Kiri Friends Core Conventions
Module Boundaries
KiriFriendsCore
The shared domain layer. No platform dependencies.
- Models:
CLIStatus,CLITask,CLICommand,CLIBridgeMessage - Protocol:
CLIBridgeProtocol, message serialization - State:
AppState,ConnectionState(value types)
KiriFriendsWatchKit
Shared watch components. watchOS-only dependencies.
- Views: Reusable SwiftUI view components
- Complications: WidgetKit complication definitions
- Extensions: SwiftUI and WatchKit extensions
KiriFriendsWatchApp
watchOS executable. Depends on Core and WatchKit.
- Entry:
KiriFriendsWatchApp.swift - Views:
ContentView,StatusView,CommandsView,HistoryView,SettingsView - Notifications:
NotificationController
KiriFriendsCLI
Mac CLI bridge executable. Depends on Core.
- Server: TCP/Unix socket server
- Client: CLI tool adapters for Claude Code, OpenCode, Codex
Communication Protocol
All messages use the JSON envelope defined in docs/core/cli-bridge.md:
struct CLIBridgeMessage: Codable {
let version: Int
let id: UUID
let type: MessageType
let payload: Payload
}
Data Model Conventions
- Use structs, not classes, for all domain models
- Make models
Codable,Hashable, andSendable - Use
UUIDfor all identifiers - Timestamps use
ISO8601DateFormatter
State Management
- Use
@Observable(Swift 6) for reference-type state containers - Use
@Stateand@Bindingfor view-local state - Propagate changes through
ObservableObjectonly when crossing module boundaries
Naming Conventions
- Types:
PascalCase(e.g.,CLIStatus,TaskResult) - Functions and properties:
camelCase(e.g.,currentTask,sendPrompt) - Files match their primary type name
- Test files:
{TypeName}Tests.swift
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.
- 12d ago First seen · 77 lines · 46 tokens per session scan A 405c552a0560
kiri-friends-core is a skill published in the GitHub repository Project-Kiri/Kiri-Friends (11 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 549 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…