concept-implementation

TypeScript rules for implementing each concept as a separate class in one file. Concepts expose named actions that take one input and return one output, plus read-only query functions for inspecting state.

In plain words
What is it for?
Use them to build and test individual concepts from their specifications, including actions and state lookups used by synchronizations.
Why use it?
They define a predictable interface between independent pieces of code and prevent queries from changing data or causing side effects.

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/eagonmeng/sync-blank/concept-implementation
Clone the repo
git clone --depth 1 https://github.com/eagonmeng/sync-blank

Made for: Cursor.

Per session 303 This file is loaded in full into every session.
When invoked 303 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 $0.00303 $0.00303
Opus 5 $0.00151 $0.00151
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured yesterday against content hash f75b170cd468, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concept-implementation 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/concept-implementation.mdc · 27 lines

What it actually says

Implementing Concepts

  • Use TypeScript
  • Each concept is a single class with the name ${name}Concept, and should be contained in a single .ts file under the directory ./concepts
  • All actions must take exactly one argument, and return one argument
  • The shape of the input and output arguments are described in the corresponding concept specification in the form of key: type
  • The names of actions must match up exactly with those in the specification
  • For the purposes of the where clause in the synchronizations, and for generally querying state, each concept may also have query functions
  • Query functions MUST start with the underscore character _ to distinguish them from actions
  • Query functions MUST NOT update state or perform side-effects
  • Query functions will also take as input a single argument with named keys, but instead return an array of such arguments corresponding to the names of the desired state. This is because query functions enable synchronizations in the where clause to e.g. declaratively find all comments related to a post, where each comment becomes a new frame for the purposes of the then clause, such as deleting all comments of a post when the post is deleted.
  • In general, if a concept is well behaving, you should not need to update it except to add query functions for the purposes of accessing state
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 · 27 lines · 303 tokens per session scan A f75b170cd468

Subscribe to this mod's changes

concept-implementation is a cursor rule published in the GitHub repository eagonmeng/sync-blank (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 303 tokens to every session, about $0.0015 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.