coding-rules

Repository-aware coding rules for implementing and reviewing maintainable code. They cover using existing project conventions, keeping changes focused, preserving contracts, structuring functions, and handling errors.

In plain words
What is it for?
Writing or modifying code, designing functions and interfaces, managing dependencies and side effects, preserving public behavior, handling errors, and performing focused refactoring.
Why use it?
They reduce accidental breaking changes, unnecessary abstractions, and unclear error behavior. They also tell the agent to follow the repository's own formatter, linter, type system, and patterns.

Skill for Claude CodeCodex

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 skills/shinpr/agentic-code/coding-rules
Any agent
npx skills add shinpr/agentic-code --skill coding-rules
Clone the repo
git clone --depth 1 https://github.com/shinpr/agentic-code

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 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 $0.00029 $0.00483
Opus 5 $0.00015 $0.00242
Sonnet 5 $0.00006 $0.00097
Haiku 4.5 $0.00003 $0.00048

Measured 2d ago against content hash 7b69a15ac05f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-rules 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 2d 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.

.agents/skills/coding-rules/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Rules

Language and Repository Rules

Use the repository's formatter, linter, type system, naming conventions, and representative code patterns. Read a language reference only when it applies:

Repository contracts and accepted design decisions take precedence over generic style preferences.

Minimal Change

  • Implement the confirmed outcome through existing mechanisms where sufficient.
  • Keep unrelated cleanup and optional hardening outside the change.
  • Remove unused code encountered inside the changed responsibility when evidence shows no current consumer remains.
  • Introduce an abstraction only when current callers share responsibility and change pressure.

Functions and Interfaces

  • Keep one coherent responsibility per function or module.
  • Use the language's idiomatic parameter and data-shape conventions.
  • Make external dependencies and side effects visible at the appropriate boundary.
  • Preserve public and shared contracts unless the approved scope changes them.
  • Prefer simple control flow; refactor complexity when it obscures behavior or error handling.

Error Handling

  • Preserve actionable error context across boundaries.
  • Convert errors only where the receiving layer needs a different contract.
  • Avoid logging the same error at every layer.
  • Keep secrets, credentials, and unnecessary personal data out of logs and messages.
  • Add fallback behavior only when a current requirement defines the degraded result.

Comments and Documentation

  • Explain non-obvious intent, constraints, or trade-offs.
  • Keep comments timeless and remove obsolete or commented-out code.
  • Update documentation when an affected consumer would otherwise act on stale information.

Refactoring

  1. Confirm the observable behavior and focused proof.
  2. Make the smallest coherent structural change.
  3. Run affected verification.
  4. Continue only when another current problem remains.

Read the full file on GitHub · 64 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 64 lines · 29 tokens per session scan A 7b69a15ac05f

Subscribe to this mod's changes

coding-rules is a skill published in the GitHub repository shinpr/agentic-code (49 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 483 once invoked, about $0.0001 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 2026-08-30.