adr-examples-must-match-code

Guidelines for keeping architecture decision record examples aligned with the code that actually ships.

In plain words
What is it for?
They help authors verify symbols and links, write copyable examples, and document implemented behavior rather than older plans.
Why use it?
They prevent readers from relying on invented, outdated, or incorrectly named APIs, files, fields, and diagnostic codes.

Cursor rule for Codex

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/prisma/orm/adr-examples-must-match-code
Clone the repo
git clone --depth 1 https://github.com/prisma/orm

Made for: Codex.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 261 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 $0.00261
Opus 5 $0.00000 $0.00130
Sonnet 5 $0.00000 $0.00052
Haiku 4.5 $0.00000 $0.00026

Measured yesterday against content hash dce8c306a851, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-examples-must-match-code 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/rules/adr-examples-must-match-code.mdc · 18 lines

What it actually says

ADR examples must match real code

When adding or editing an ADR, every reference to the codebase — code examples and prose mentions of type names, function names, field names, diagnostic-code strings, and file paths — must match the shipped source, not a draft or a memory of the API:

  • Prefer examples that are copy/pasteable and reflect the current API.
  • Avoid inventing fluent helper syntax unless it already exists in the codebase.
  • Verify each cited symbol, field, diagnostic code, and file path by searching the source before documenting it — don’t trust the name you remember or the name a spec used.
  • Close-out ADRs are drawn from a project spec that predates implementation. Field and symbol names routinely get renamed during the slices, so the spec is the least reliable naming source by the time the ADR is written. Treat the spec as intent; confirm every name against the merged code.
  • Resolve every relative link from the ADR’s own directory depth (ADRs live one level deeper than projects/), so ../ counts are easy to get wrong.
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 · 18 lines · 0 tokens per session scan A dce8c306a851

Subscribe to this mod's changes

adr-examples-must-match-code is a cursor rule published in the GitHub repository prisma/orm (47,579 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 261 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 2026-08-30.