write-code-rules

Writes project code-rules.md with enforcement channels for each deliberated coding rule.

Updated Jun 12, 2026
One-click install
npx skills add https://github.com/lucolucus/mismagent --skill write-code-rules-lucolucus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: write-code-rules
Source: https://github.com/lucolucus/mismagent/tree/main/plugins/mismagent/skills/write-code-rules
Command: npx skills add https://github.com/lucolucus/mismagent --skill write-code-rules-lucolucus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coding standards often decay into unread documents because nothing enforces them. This Skill writes the project's code-writing rules as a visible file where every rule carries an explicit enforcement channel, so a rule without enforcement is never written. ## Core Features & Use Cases - Enforcement-channel binding: Each rule is classified as mechanical (gate dependency/style lint such as Konsist, ArchUnit, dependency-cruiser, or import-linter), discursive (code-review criterion), or structural (citation of the owning skill or gate). - Project-level output: Produces <output_dir>/code-rules.md next to profile.md and architecture.md, with the profile's code_rules binding updated so workers and code review receive it automatically. - Delta-based updates: On later features it proposes only deltas against the existing file, keeping one source of truth. - Use Case: During the mismAgent model movement, after the user deliberates rules in the ARCH_PROPOSAL checkpoint and the stack ADR is set, the architect invokes this Skill to emit code-rules.md with lint tool and config path pinned per stack. ## Quick Start Ask the mismagent-architect during the model movement to write the project's code-rules.md from the deliberated ARCH_PROPOSAL rules after the stack ADR is decided.

Frequently Asked Questions about write-code-rules

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce coding rules automatically in a project?

Bind each rule to an enforcement channel: mechanical rules go to a dependency or style lint wired into the gate and CI, discursive rules become code-review criteria, and structural rules cite the owning skill or gate. A rule with no channel is not written.

What dependency lint tools enforce architecture rules per stack?

JVM/Kotlin uses Konsist or ArchUnit, TypeScript uses dependency-cruiser or eslint-plugin-boundaries, and Python uses import-linter. The architect proposes the tool per stack, and its config lives in the side's repo, derived from the architecture module map.

Where should project coding standards live so developers actually read them?

Place them in a project-level code-rules.md file next to profile.md and architecture.md, not per-feature. The profile's code_rules binding delivers them to workers and code review through the profile they already read.

Why is grep the wrong tool for enforcing dependency rules?

A dependency rule is a graph property, and POSIX grep is blind to fully qualified names, build files, and aliases. Use the stack's dependency lint instead, with config wired at wave 0 so it runs in the worker's gate loop, verifier step 2, and CI.

When is the write-code-rules skill invoked in the mismAgent flow?

It is invoked by mismagent-architect in pass-2 of the model movement, after the user deliberated the rules inside the ARCH_PROPOSAL checkpoint and after the stack ADR, since the lint choice depends on the stack.