verify-code

verify-code is a skill for Claude Code, Codex from sponge-b0b/Polaris. It costs 33 tokens per session (1,840 once invoked), scanned A, original, Apache-2.0.

A targeted verification check for changed Python files and their directly affected tests. It reviews the difference, checks related contracts, and runs relevant syntax, formatting, type, and test checks.

In plain words
What is it for?
Use it after editing Python code to check whitespace, syntax, formatting, static types, contract impacts, and focused tests, while reporting unrelated pre-existing problems.
Why use it?
It catches defects in the active change without turning every small edit into a full repository-wide test run. When a shared contract changes, it also finds the internal users that may be affected.

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/verify-code
Any agent
npx skills add sponge-b0b/Polaris --skill verify-code
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 verify-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/sponge-b0b/polaris/verify-code.svg)](https://agentmods.dev/skills/sponge-b0b/polaris/verify-code)
Your own site
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/verify-code"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/verify-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,840 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 $0.00033 $0.01840
Opus 5 $0.00016 $0.00920
Sonnet 5 $0.00007 $0.00368
Haiku 4.5 $0.00003 $0.00184

Measured 3d ago against content hash dd1ff17c83ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-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 3d 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/verify-code/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Targeted Codebase Verification Standards

Objective

Verify changes introduced by the current workspace or active ticket without broadening execution into repository-wide verification.

$coding-standards owns coding policy. Verify applicable requirements without duplicating that skill.

Repository-wide discovery is required when necessary to prove that an authoritative contract change has no stale internal consumers. Broaden discovery, not verification indiscriminately.

Guardrails

  • Verify only the active change and directly affected tests.
  • Resolve target files before verification.
  • When a shared contract changes, discover its complete affected consumer set before declaring verification scope complete.
  • Do not refactor unrelated code, weaken configuration, or add pass-only suppressions.
  • Shell permissions do not authorize broader verification.
  • Do not bypass repository command guards.
  • Deterministic whitespace defects owned by the active change are mechanical fixes: fix them, rerun the check, and continue without asking.
  • Do not modify semantic content while fixing whitespace.
  • Unrelated pre-existing whitespace remains report-only.

1. Identify Targets

If called by $implement-ticket with a ticket baseline, include committed Python changes since that baseline:

git diff --name-only --diff-filter=ACMR <ticket-baseline>...HEAD -- '*.py'

Also include unstaged, staged, and untracked Python changes:

git diff --name-only --diff-filter=ACMR -- '*.py'
git diff --cached --name-only --diff-filter=ACMR -- '*.py'
git ls-files --others --exclude-standard -- '*.py'

Use the deduplicated union as Python verification targets.

If no ticket baseline applies, use workspace changes only.

Do not broaden scope because no Python targets exist.

Contract-Impact Closure

Inspect the active diff before finalizing the target set.

This gate applies when the change modifies a shared internal contract or semantic owner, including an API/call signature, protocol/interface, identity source, lifecycle responsibility, canonical representation, enum/value contract, configuration key, or other reusable boundary.

Read the full file on GitHub · 243 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. 3d ago First seen · 243 lines · 33 tokens per session scan A dd1ff17c83ab

Subscribe to this mod's changes

verify-code is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,840 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

nornweave-api

Give AI agents their own email inboxes using the NornWeave API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, retrieving threads, searching messages, or integrating with email providers (Mailgun, SES, SendGrid, Resend). NornWeave provides LLM-ready markdown parsing and…

DataCovey/nornweave · 77 tokens

commit-push

Commit and push the changes made on this chat session to the current branch. Use best practices from Conventional Commits.

DataCovey/nornweave · 27 tokens

commit

Commit the changes made on this chat session to the current branch. Use best practices from Conventional Commits.

DataCovey/nornweave · 23 tokens

hybrid-ralph

Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with dependency resolution, and provides context-filtered agents for efficient multi-story development.

Taoidle/plan-cascade · 52 tokens

mega-plan

Project-level multi-task orchestration system. Manages multiple hybrid:worktree features in parallel with dependency resolution, coordinated PRD generation, and unified merge workflow.

Taoidle/plan-cascade · 35 tokens

planning-with-files

Implements Manus-style file-based planning for complex tasks. Creates taskplan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear and optional Git worktree mode.

Taoidle/plan-cascade · 62 tokens