Polaris: Skill for Claude Code

.agents/skills/verify-ticket-closure/SKILL.md

verify-ticket-closure is a skill for Claude Code from sponge-b0b/Polaris. It costs 43 tokens per session (4,796 once invoked), scanned A, original, Apache-2.0.

A verifier that independently decides whether an implementation ticket is truly complete. It checks the candidate against the ticket’s required conditions instead of relying on the person who made the changes.

In plain words
What is it for?
Use it to review closure evidence for ordinary implementation tickets and specification-review remediation tickets.
Why use it?
It prevents an implementation from certifying its own completion and helps catch missing requirements before a ticket is closed.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

This is sponge-b0b/Polaris's own configuration. It tells Claude Code how to work on Polaris itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Polaris configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sponge-b0b/Polaris. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sponge-b0b/Polaris/main/.agents/skills/verify-ticket-closure/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sponge-b0b/Polaris

Made for: Claude Code.

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-ticket-closure

README.md
[![agentmods](https://agentmods.dev/badge/skills/sponge-b0b/polaris/verify-ticket-closure/github.svg)](https://agentmods.dev/skills/sponge-b0b/polaris/verify-ticket-closure)
Your own site
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/verify-ticket-closure"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/verify-ticket-closure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verify-ticket-closure

Your own site · 80×15
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/verify-ticket-closure"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/verify-ticket-closure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00043 $0.04796
Opus 5 $0.00022 $0.02398
Sonnet 5 $0.00009 $0.00959
Haiku 4.5 $0.00004 $0.00480

Measured today against content hash b65df92213cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

verify-ticket-closure 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 today.

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-ticket-closure/SKILL.md · 447 lines

How it starts

The opening of the file, as written. The whole thing — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Ticket Closure

Independently certify or reject closure of one immutable ticket candidate.

This skill is the single semantic closure authority for both ordinary Implementation Tickets and Spec Review remediation tickets.

The implementation actor may propose closure evidence, but it may not certify its own candidate.

Remediation extends the acceptance universe. It does not create a second verifier or a second verdict.

Certified Semantic Domain Finality

This section is authoritative and strengthens every later domain-construction/closure rule in this file.

When PASS depends on closing a material finite/discoverable semantic domain, the fresh verifier is not only proving the candidate. It is also certifying the membership interpretation used to define that domain.

For every such domain, preserve one compact Certified Closure Domain record in the verifier PASS returned to $implement-ticket:

Certified Closure Domain: <stable ND/domain ID>
Parent claim/root: <AC-n / RB-n when applicable>
Authority identity: <exact durable source identities/hashes when available>
Membership predicate: <what makes a candidate a member>
Dimensions / authoritative source sets: <explicit sets or bounded sources>
Closure criterion: <expected count | independently checkable open-world criterion>
Expected/generated/inspected/dispositioned: <counts when finite>
Material out-of-domain boundary observations: <concise list/families when needed>
Finality: frozen-under-unchanged-authority

A domain record is required when domain construction materially contributes to semantic PASS. Do not hide the final membership interpretation only inside narrative evidence.

Before PASS require:

Material closure domains required: <n>
Certified closure-domain records: <n>
Missing domain records: 0
Unresolved domain identities: 0

The verifier must derive each record from the same durable authority/membership predicate already required below. The record does not broaden that authority.

Read the full file on GitHub · 447 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. today Changed · +6 lines b65df92213cb
  2. 4d ago Changed · +153 lines 56764d67cade
  3. 6d ago First seen · 288 lines · 43 tokens per session scan A f755c054198e

Subscribe to this mod's changes

verify-ticket-closure is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 4,796 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 2026-09-04.