Borrowing it
Nothing to install: this file belongs to aleemrehmtulla/kytelink. 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/aleemrehmtulla/kytelink/main/CLAUDE.mdgit clone --depth 1 https://github.com/aleemrehmtulla/kytelinkWrote 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/aleemrehmtulla/kytelink/claude-md)<a href="https://agentmods.dev/instructions/aleemrehmtulla/kytelink/claude-md"><img src="https://agentmods.dev/badge/instructions/aleemrehmtulla/kytelink/claude-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/aleemrehmtulla/kytelink/claude-md"><img src="https://agentmods.dev/badge/instructions/aleemrehmtulla/kytelink/claude-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 | $0.02524 | $0.02524 |
| Opus 5 | $0.01262 | $0.01262 |
| Sonnet 5 | $0.00505 | $0.00505 |
| Haiku 4.5 | $0.00252 | $0.00252 |
Grade A, and why
kytelink CLAUDE.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 9d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Kytelink is developed agent-first: AI agents boot the product, log in with known credentials, and actually use it. If you're an agent landing in this repo cold, you should be driving the product within a minute — read this section first.
Run the product as an agent
pnpm install
pnpm agents
That's the whole bootstrap: on a fresh clone pnpm agents runs the setup
wizard non-interactively (pnpm run setup --all — writes .env with fresh
secrets, starts the full Docker stack, migrates), then seeds the agent
accounts, then boots every app with AGENT_MODE=true on dev port + 1000,
so an agent session never collides with a human dev's pnpm dev session on
the same machine:
| App | Dev port | Agent port |
|---|---|---|
| web (editor + public profile) | 3000 | 4000 |
| landing (kytelink.com marketing) | 3001 | 4001 |
| admin | 3002 | 4002 |
| api (Fastify + tRPC) | 3003 | 4003 |
| local CDN (shared, not shifted) | 5003 | 5003 |
Logins (OTP is always 000000 in agent mode, for any *@kytelink.dev
address):
[email protected]— personal org, one published@agentkyte, one unpublished draft, MANAGER in the seeded agency org (org_agency_demo).[email protected]— platformADMIN, full admin app access.
Fast path for scripted flows: POST {api}/auth/dev-login {"email":"..."}
mints a real session and sets the signed cookie in one call — skips the
login screen entirely.
One-line tour: web editor on :4000, admin on :4002 — log in as
[email protected], OTP 000000.
Both login mechanisms exist ONLY when AGENT_MODE=true, and apps/api
refuses to boot if AGENT_MODE=true && NODE_ENV=production. Full detail:
git show faa5f4d^:rewrite/24-agents.md.
Stack lifecycle: pnpm dev and pnpm agents each write a lockfile
(.dev-dev.lock / .dev-agents.lock) recording their process tree. A new run
first reaps whatever a dead session left behind, and refuses to start while
the previous orchestrator is still alive — pnpm stop tears down both stacks
from anywhere. Never start app processes directly (pnpm --filter ... dev,
raw next dev/tsx watch); processes started outside the orchestrators are
invisible to the reaper and will leak when the session dies.
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.
- 9d ago First seen · 196 lines · 2,524 tokens per session scan A e28049067aaf
kytelink CLAUDE.md is an instructions file published in the GitHub repository aleemrehmtulla/kytelink (109 stars, last pushed 6d ago), licensed MIT. It adds 2,524 tokens to every session, about $0.0126 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 instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.