cairn-commit-network

A project rule for commits that run Cairn hooks, which are automatic scripts triggered by Git commits. It requires unrestricted network access because the hook calls Claude or Cursor Agent to create a distilled record.

In plain words
What is it for?
Use it when committing changes in a project with Cairn hooks, especially when the commit needs network access or broader hook filesystem access.
Why use it?
It prevents commits from failing or producing incomplete records when the default agent network sandbox interferes with those API calls.

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/yungc0de/git-cairn/cairn-commit-network
Clone the repo
git clone --depth 1 https://github.com/YUNGC0DE/git-cairn

Made for: Cursor.

Per session 188 This file is loaded in full into every session.
When invoked 188 The same file — it is already loaded in full.
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 $0.00188 $0.00188
Opus 5 $0.00094 $0.00094
Sonnet 5 $0.00038 $0.00038
Haiku 4.5 $0.00019 $0.00019

Measured yesterday against content hash f59d92e3329d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cairn-commit-network 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/cairn-commit-network.mdc · 21 lines

What it actually says

Cairn commits from Cursor Agent

Cairn's prepare-commit-msg hook calls claude / cursor-agent for distillation. The default Cursor Agent sandbox injects HTTP(S)_PROXY to a local seatbelt proxy; cursor-agent then fails with SSL EPROTO … packet length too long, and the record collapses to metadata-only.

When running git commit (or any command that triggers cairn hooks) from the Agent shell:

  • Request required_permissions: ["full_network"] at minimum
  • Prefer ["all"] if the commit also needs unrestricted git hook filesystem access
  • Do not commit under the default sandbox — distillation will not reach the API

A normal external terminal is fine; only the Agent sandbox breaks this.

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 · 21 lines · 188 tokens per session scan A f59d92e3329d

Subscribe to this mod's changes

cairn-commit-network is a cursor rule published in the GitHub repository YUNGC0DE/git-cairn (2 stars, last pushed 24d ago), licensed MIT. It adds 188 tokens to every session, about $0.0009 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.