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 instructions/creative-int/kumori-plugins/agents-mdgit clone --depth 1 https://github.com/creative-int/kumori-pluginsWhat 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 | $0.00685 | $0.00685 |
| Opus 5 | $0.00342 | $0.00342 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
kumori-plugins AGENTS.md 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kumori plugins - agent guide
Public distribution repo for kumori: the portable Agent Plugins 1.0.0 package (plugin.json, mcp.json, skills/) plus generated setup for Codex, Claude Code, Cursor, Windsurf, VS Code, and generic Streamable HTTP clients, .mcp.json, MCP Registry server.json, and the kumori sticker skill. External agents connect to kumori's remote MCP endpoint and run the sticker loop.
The one product rule
kumori is always image + style in → sticker out. There is no prompt. Never introduce prompt language, subject descriptions, or free-text style instructions into the skill, the config copy, or any manifest. The image is the subject; the style slug is the only creative decision.
The one repo rule: generate, don't hand-edit
kumori.config.ts is the single source of truth. Every manifest — the
portable plugin.json and mcp.json, .mcp.json, .claude-plugin/*,
.codex-plugin/*, .agents/plugins/marketplace.json, .cursor-plugin/*,
server.json, clients/*, and the README AUTO-GENERATED install block —
is emitted by tooling/generate.ts:
pnpm generate
pnpm verify
CI runs check:generated and fails on drift. Never hand-edit generated files.
Agent Plugins conformance
plugin.jsonandmcp.jsonfollow the closed 1.0.0 schemas;skills/follows the Agent Skills spec.tooling/smoke.tsenforces the spec rules (closed field sets, §5.5 naming, HTTPS remote URL, no configured headers).schemas/1.0.0/is vendored verbatim from agentplugins/agent-plugins-spec (Apache-2.0) so validation stays hermetic.- Auth is client-owned OAuth against the user's kumori account. The endpoint answers 401 with OAuth discovery metadata until the client authorizes. Never add tokens, headers, or credential fields anywhere in this repo.
Scope
- v0: portable Agent Plugins core, six client setups, three plugin-system
manifests,
.mcp.json,server.json, and one sticker skill. - Live origin:
https://mcp.kumori.camera/(POST / is the MCP endpoint). - The server source lives in the kumori monorepo (
apps/mcp); this repo is distribution only — no product runtime surface.
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 · 60 lines · 685 tokens per session scan A 1662ac3f8fcd
kumori-plugins AGENTS.md is an instructions file published in the GitHub repository creative-int/kumori-plugins (0 stars, last pushed 17d ago), licensed MIT. It adds 685 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.