ai-working-rules

Shared working rules for an AI coding agent in a repository, covering updates, testing, redirects, secrets, and evidence.

In plain words
What is it for?
Guiding repository changes, deciding whether to update or add files, defining tests and proof artifacts, checking redirects, and blocking exposed secrets.
Why use it?
They set expectations for making safe, reviewable changes and for proving that the result works before finishing.

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/hariharapanigrahy/layerkit/ai-working-rules
Clone the repo
git clone --depth 1 https://github.com/hariharapanigrahy/layerkit

Made for: Cursor.

Per session 97 This file is loaded in full into every session.
When invoked 97 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 $0.00097 $0.00097
Opus 5 $0.00048 $0.00048
Sonnet 5 $0.00019 $0.00019
Haiku 4.5 $0.00010 $0.00010

Measured 3d ago against content hash 8b46748b8c61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-working-rules 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 3d 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.

.cursor/rules/ai-working-rules.mdc · 16 lines

What it actually says

Read and follow AI_WORKING_RULES.md.

In short:

  • prefer update/delete over adding new files
  • define what must pass, proof artifact, and fallback before implementation
  • prove strategic redirects before broad rewrites or deletions
  • keep test backing proportional to implementation size
  • treat hardcoded secrets as release blockers in public/shared repos
  • work collaboratively and evidence-first
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. 3d ago First seen · 16 lines · 97 tokens per session scan A 8b46748b8c61

Subscribe to this mod's changes

ai-working-rules is a cursor rule published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 26d ago), licensed MIT. It adds 97 tokens to every session, about $0.0005 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.