Borrowing it
Nothing to install: this file belongs to pubky/pubky-app. 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/pubky/pubky-app/dev/AGENTS.mdgit clone --depth 1 https://github.com/pubky/pubky-appWrote 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/instructions/pubky/pubky-app/agents-md)<a href="https://agentmods.dev/instructions/pubky/pubky-app/agents-md"><img src="https://agentmods.dev/badge/instructions/pubky/pubky-app/agents-md/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/instructions/pubky/pubky-app/agents-md"><img src="https://agentmods.dev/badge/instructions/pubky/pubky-app/agents-md.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 | $0.03330 | $0.03330 |
| Opus 5.5 | $0.01332 | $0.01332 |
| Sonnet 5.5 | $0.00666 | $0.00666 |
| Haiku 4.5 | $0.00333 | $0.00333 |
Grade A, and why
pubky-app 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pubky App
Decentralized social app: Next.js 16 App Router, React 19 with the React Compiler, TypeScript, Tailwind v4 + Shadcn UI, Zustand,
Dexie (IndexedDB), TanStack Query. Package name franky. Local-first: writes go to Dexie first and sync to the homeserver;
reads come from Dexie and fall back to Nexus. This file is the entry point for every AI agent (Claude Code, Codex, Cursor);
it indexes docs/, which is canonical and wins over anything here (docs/development-workflow.md is the long version).
Commands
Node 24 (.nvmrc), dependencies via npm ci. The pre-commit hook runs lint-staged then npm run typecheck.
| Task | Command |
|---|---|
| Dev server (port 3000) | npm run dev (staging defaults are built in, no .env needed) |
| Format, lint, types | npm run format:check, npm run lint, npm run typecheck |
| Unit tests (jsdom) | npm test (~13k tests, minutes); one file npm test -- <path>; one name npm test -- -t "x" |
| Visual regression (VRT) | npm run test:vrt (npm run test:vrt:setup once); baselines are CI-owned, never commit local |
| Production build | npm run build (next build --webpack) |
| E2E (Cypress) | npm run test:e2e; needs the full pubky-stack, not runnable from a bare checkout |
Architecture (src/core)
UI (user actions) → Controllers → Application → Services → Models
Coordinators (system) ↗ ↓ ↓
Stores Pipes Database
Hard constraints (review-enforced, not compiler-enforced; docs/architecture.md):
- Controllers NEVER call Services directly and never do IO; they go through Application.
- Coordinators NEVER call Application; they go through Controllers.
- Application NEVER accesses Stores and never calls Controllers; only Controllers manage stores.
- Services NEVER access Stores, except session reads in
HomeserverService/LocksServiceviagetState()(ADR-0004/0024), including auth failure metadata and the Locks creator-owner check against the current app account; reads only, never writes. - Pipes are pure: NO IO, NO side effects. Services never call up. Models touch Dexie only.
- Cross-Application calls (ADR-0009): only PostApplication, NotificationApplication, BootstrapApplication, MigrationApplication, HotApplication, PostStreamApplication and TtlApplication may call other Applications; acyclic; depth 1, with one depth-2 exception: PostApplication | NotificationApplication | TtlApplication → PostStreamApplication → FileApplication.
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 Changed · +4 lines · +104 tokens per session 409498686cea
- 9d ago Changed · +1 lines · +20 tokens per session 56fefd875dc2
- 11d ago Changed · +2 lines · +49 tokens per session 53ca1da45134
- 12d ago Changed · -1 lines · -4 tokens per session 4c88eaf96bc8
- 20d ago Changed · +1 lines · +33 tokens per session 5d7481252ef0
- 22d ago Changed · +2 lines · +39 tokens per session b74e38eb53c3
- 25d ago Changed · +1 lines · +57 tokens per session 25287ff98590
- 28d ago Changed · +9 tokens per session 46e0e5597267
- 1mo ago Changed · +25 tokens per session 0a05eab56ee9
- 1mo ago First seen · 151 lines · 2,998 tokens per session scan A 73d0df82631d
pubky-app AGENTS.md is an instructions file published in the GitHub repository pubky/pubky-app (26 stars, last pushed today), licensed MIT. It adds 3,330 tokens to every session, about $0.0133 per session on Opus 5.5. 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 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.