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.
npx agentmods add rules/hamzaamjad/cursor-rules/109-chain-of-codegit clone --depth 1 https://github.com/hamzaamjad/cursor-rulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/hamzaamjad/cursor-rules/109-chain-of-code)<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/109-chain-of-code"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/109-chain-of-code.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01292 | $0.01292 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
109-chain-of-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chain of Code (CoC) Reasoning
Purpose
Chain of Code improves reasoning accuracy by generating and executing code for verification, calculation, and logical validation. This approach achieves 17.9% improvement on arithmetic tasks and 11% on commonsense reasoning by treating problems as executable programs rather than abstract reasoning tasks.
Core Principles
Chain of Code transforms ambiguous reasoning into precise, verifiable computation. Rather than attempting mental calculations or logical deductions, the pattern generates executable code that demonstrates correctness through execution. This approach eliminates calculation errors, ensures logical consistency, and provides transparent verification of results.
The pattern applies to any problem involving arithmetic operations, logical reasoning, data transformations, pattern matching, or state-based workflows. By converting these problems into code, the reasoning process becomes reproducible, testable, and unambiguous.
Implementation Requirements
Effective Chain of Code implementation requires systematic translation of problems into executable formats. Begin with clear problem decomposition, identifying calculable components and logical relationships. Generate code that explicitly represents each reasoning step, including intermediate calculations and state transitions.
The code must include comprehensive test cases that verify correctness across edge conditions. These tests serve as both validation mechanisms and documentation of expected behavior. Each code block should execute within defined safety constraints, avoiding operations that could impact system state or consume excessive resources.
Language selection follows problem domain requirements. Python serves well for data analysis and general computation. JavaScript handles web-related logic and asynchronous operations effectively. SQL excels at set operations and data queries. Regular expressions provide powerful pattern matching capabilities. The choice depends on which language most naturally expresses the problem solution.
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.
- 4d ago First seen · 93 lines · 1,292 tokens per session scan A c682a4287eb9
109-chain-of-code is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 1,292 tokens to every session, about $0.0065 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.