kit-settings

A repository rule for keeping each kit's operational settings in a committed settings.json file. The file currently records the kit's versioning method and current release version.

In plain words
What is it for?
It is for storing a kit's current semantic version and supporting workflows that read, update, and publish that version.
Why use it?
It gives each kit one tracked source of truth for its release state, helping keep version numbers and Git tags aligned.

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/secondlifes/code-intel/kit-settings
Clone the repo
git clone --depth 1 https://github.com/SecondLifes/code-intel

Made for: Cursor.

Per session 697 This file is loaded in full into every session.
When invoked 697 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 $0.00697 $0.00697
Opus 5 $0.00349 $0.00349
Sonnet 5 $0.00139 $0.00139
Haiku 4.5 $0.00070 $0.00070

Measured yesterday against content hash f8f0826c21aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kit-settings 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/kit-settings.mdc · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kit Settings (settings.json) — Rules

Every kit ships a settings.json at its own root (next to AGENTS.md, README.md) — committed to git, unlike analysis/ (gitignored, local-only). Think of it like a package.json's version field: it is this repo's own source of truth for its own operational state, not a shared cross-kit file like the workspace root's template-vars.json (which holds identity/legal values substituted once at kit-creation time and never touched again).

Current schema

{
  "$comment": "Per-kit operational settings — committed to git. Extend with new top-level keys as needs arise; document each addition here and in this file's own $comment.",
  "versioning": {
    "scheme": "semver",
    "current_version": "0.1.0"
  }
}
  • versioning.current_version — this kit's current released version. This is the value the fix-publication workflow reads before tagging and writes back after bumping — see .agents/skills/rad-prompt-studio/references/prompts/edit-base-prompt.md's Golden Rule 7. The annotated git tag (vMAJOR.MINOR.PATCH) must always match this value; if they ever disagree, settings.json is correct and the tag needs to catch up (or vice versa if a tag was created without updating this file — audit which one is stale from the actual git tag list and the CHANGELOG, don't guess).
  • versioning.scheme — currently always "semver". Present so a future non-semver kit isn't forced into the wrong assumption silently.

Extensibility

This file is deliberately small today and expected to grow — new top-level keys get added here as real needs arise (the workspace owner described this explicitly: "ileride çok genişletilebilir"). When adding a new key:

  1. Document it in this rule file (schema + meaning) before or alongside introducing it in code/workflow.
  2. Keep it kit-local operational state — identity/legal/contributor data still belongs in the workspace root's template-vars.json, not here.
  3. Never store secrets (API keys, tokens, credentials) in this file — it is committed and public once the kit is published.

Read the full file on GitHub · 61 lines

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 · 61 lines · 697 tokens per session scan A f8f0826c21aa

Subscribe to this mod's changes

kit-settings is a cursor rule published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 697 tokens to every session, about $0.0035 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.