tell-github-setup

Local-only rules for a GitHub repository setup feature that clones a repository, installs its dependencies, detects how it runs, and starts a development server.

In plain words
What is it for?
Use them when building or reviewing repository setup endpoints, setup guards, job states, stale captures, or manual preview-URL fallback.
Why use it?
They prevent repository setup endpoints from being exposed in production and make setup failures, duplicate requests, and active local URLs clear to the developer.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/ashishpatill/tell-proof/tell-github-setup
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 191 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00191
Opus 5 $0.00000 $0.00096
Sonnet 5 $0.00000 $0.00038
Haiku 4.5 $0.00000 $0.00019

Measured yesterday against content hash 42652c08dd3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tell-github-setup 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 yesterday.

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.

.cursor/rules/tell-github-setup.mdc · 16 lines

What it actually says

GitHub setup rules

  • /api/setup/* clones repos, runs install scripts, and spawns dev servers — local dev only.
  • Guard with setup-guard.ts and TELL_DISABLE_REPO_SETUP=1 for production/deploy.
  • Never expose setup endpoints on public deploy without the guard enabled.
  • Job states: cloning → installing → detecting → starting → waiting → ready | needs-manual | error.
  • Block duplicate setup clicks; hide stale captures while a job is running.
  • Surface plain-language success/failure; never leave Ashish guessing which localhost URL is active.
  • On failure, show what was detected from README/package.json and offer manual URL paste.
Changes

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.

  1. yesterday First seen · 16 lines · 0 tokens per session scan A 42652c08dd3b

Subscribe to this mod's changes

tell-github-setup is a cursor rule published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 191 tokens. 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.