coding-standards

coding-standards is a skill for Claude Code, Codex from sponge-b0b/Polaris. It costs 81 tokens per session (3,164 once invoked), scanned A, original, Apache-2.0.

A set of rules for writing and reviewing Python code in a particular repository. It covers readable design, project data rules, types, precision, tests, formatting, and monitoring-related requirements.

In plain words
What is it for?
It is for creating, changing, refactoring, fixing, or reviewing Python source code and tests. It helps decide which project settings and architectural documents should guide the work.
Why use it?
It reduces inconsistent code and prevents changes that pass a generic check but violate the project's own rules. It also tells developers to inspect repository instructions and configuration before editing.

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/sponge-b0b/polaris/coding-standards
Any agent
npx skills add sponge-b0b/Polaris --skill coding-standards
Clone the repo
git clone --depth 1 https://github.com/sponge-b0b/Polaris

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for coding-standards

README.md
[![agentmods](https://agentmods.dev/badge/skills/sponge-b0b/polaris/coding-standards.svg)](https://agentmods.dev/skills/sponge-b0b/polaris/coding-standards)
Your own site
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/coding-standards"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/coding-standards.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,164 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 $0.00081 $0.03164
Opus 5 $0.00041 $0.01582
Sonnet 5 $0.00016 $0.00633
Haiku 4.5 $0.00008 $0.00316

Measured 4d ago against content hash 25e824675a17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-standards 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.

.agents/skills/coding-standards/SKILL.md · 481 lines

How it starts

The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Standards

Apply these standards whenever creating, modifying, refactoring, fixing, or reviewing Python source code.

Optimize for correct, readable, maintainable Python with the minimum total complexity necessary.

Scope and Precedence

These rules apply to Python source and tests.

Before changing code:

  1. Read applicable repository instructions such as AGENTS.md.
  2. Inspect relevant code, callers, tests, and established patterns.
  3. Inspect repository configuration such as pyproject.toml, ruff.toml, and mypy.ini.
  4. Follow repository-configured Python, Ruff, Mypy, formatting, and testing rules over generic defaults in this skill.
  5. Follow authoritative ADRs and docs/current/ sources when a coding rule depends on project architecture or semantics.

Do not modify lint, formatting, typing, or test configuration merely to make code pass unless changing that policy is itself part of the task.

A direct user requirement or documented repository rule overrides a design preference here. Required correctness, security, data integrity, domain contracts, scoring semantics, and observability are not optional simplifications.


Polaris Non-Negotiables

Data-Contract Boundaries

When changing application-service, intelligence, runtime, persistence, or other data-contract boundaries, read:

docs/current/domain-contracts-data-semantics-contract-semantics.md

Follow its canonical classification and boundary rules.

In particular:

  • exchange stable internal semantics through typed objects;
  • use mappings only at approved serialization, vendor, telemetry, persistence, report, artifact, runtime, or transport boundaries;
  • do not hide stable business dimensions in generic metadata or undifferentiated mappings;
  • promote stabilized semantics from extension mappings into explicit typed fields;
  • distinguish fallback or unavailable values from canonical observations.

For AI-adjacent outputs, preserve the applicable RiskAuthorityContract requirements defined by the same authoritative source.

Read the full file on GitHub · 481 lines

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. 4d ago First seen · 481 lines · 81 tokens per session scan A 25e824675a17

Subscribe to this mod's changes

coding-standards is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed today), licensed Apache-2.0. It adds 81 tokens to every session and 3,164 once invoked, about $0.0004 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.