coding-standards

The project's baseline rules for writing and checking code. They cover where content belongs, TypeScript and module conventions, offline operation, version updates, and required verification commands.

In plain words
What is it for?
Adding or updating agent knowledge, installed artifacts, TypeScript code, command-line behavior, generated files, versions, and the project's build and static-evaluation checks.
Why use it?
They give contributors consistent boundaries for changing the codebase and help catch changes that would break its build, audit, or offline checks.

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/doidor/agentrig/coding-standards
Clone the repo
git clone --depth 1 https://github.com/doidor/agentrig

Made for: Cursor.

Per session 354 This file is loaded in full into every session.
When invoked 354 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 $0.00354 $0.00354
Opus 5 $0.00177 $0.00177
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00035 $0.00035

Measured yesterday against content hash ece3daa06b6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-standards 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/coding-standards.mdc · 22 lines

What it actually says

Coding standards (reflex)

  • Author harness content in knowledge/ (plain text); never hard-code it in src/.
  • Import @github/copilot-sdk only under src/agent/; all model access goes through the AgentProvider interface.
  • Keep knowledge/templates/eval/checks.json in sync when adding/removing an installed artifact, or the audit silently ignores it.
  • Write TypeScript that compiles clean under strict + noUncheckedIndexedAccess; handle null/undefined explicitly.
  • Use ESM only: include the .js extension in relative import paths (NodeNext); no require/CommonJS.
  • Keep every command working with --dry-run and offline — eval --static and doctor must never need a model or network.
  • Never edit generated dist/; change src/ and rebuild with npm run build.
  • Bump package.json version and knowledge/manifest.json knowledgeVersion together when changing installed artifacts.
  • Verify with the smoke checks before handoff (npm run build + node dist/cli.js eval --static .); there is no lint or unit-test suite to lean on.
  • No secrets in source. Do not weaken checks.json or skip the audit just to make a score pass.

Specialized, glob-scoped rules can live alongside this baseline.

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 · 22 lines · 354 tokens per session scan A ece3daa06b6a

Subscribe to this mod's changes

coding-standards is a cursor rule published in the GitHub repository doidor/agentrig (5 stars, last pushed 1mo ago), licensed MIT. It adds 354 tokens to every session, about $0.0018 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.