Polaris: Skill for Claude Code

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

verify-ticket-decomposition is a skill for Claude Code, Codex from sponge-b0b/Polaris. It costs 46 tokens per session (3,829 once invoked), scanned A, original, Apache-2.0.

An independent checker for a proposed breakdown of work into tickets, where tickets are individual tasks or issues. It checks whether the proposal preserves the requirements without omissions or hidden design decisions.

In plain words
What is it for?
It helps certify or reject one frozen ticket proposal before a person approves it; it does not rewrite, publish, or implement the proposal.
Why use it?
It catches missing details, distorted requirements, and work that was quietly left for the implementer to decide.

Skill for Claude CodeCodex

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

This is sponge-b0b/Polaris's own configuration. It tells Claude Code and Codex 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-decomposition/SKILL.md
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-ticket-decomposition

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/verify-ticket-decomposition"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/verify-ticket-decomposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,829 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 $0.00046 $0.03829
Opus 5.5 $0.00018 $0.01532
Sonnet 5.5 $0.00009 $0.00766
Haiku 4.5 $0.00005 $0.00383

Measured 10d ago against content hash da5e3b2e19ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-ticket-decomposition 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 10d 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-ticket-decomposition/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Ticket Decomposition

Independently certify or reject one exact frozen $to-tickets proposal before human approval.

$to-tickets may author and self-check the decomposition, but it may not independently certify its own semantic carry.

This verifier exists to catch omissions, semantic compression, misrouting, or hidden design delegation in the exact proposed ticket contracts. It is not a second decomposition author, a general adversarial review, or an implementation verifier.

Invocation Boundary

Normal invocation is internal to $to-tickets after parent-owned TICKET PROPOSAL READINESS: PASS and before the proposal is shown for approval.

For one substantive proposal lifecycle, $to-tickets dispatches exactly one genuinely fresh verifier context executing this skill. The parent remains the orchestration and mutation owner.

The fresh verifier is:

  • fresh — it did not author, route, or repair the proposal;
  • non-mutating — it may read/search/inspect only;
  • non-delegating — it may not spawn another semantic verifier or challenger;
  • candidate-bound — it certifies exactly one supplied proposal identity and source state;
  • source-grounded — parent matrices and findings are retrieval maps, not semantic authority.

If the verifier returns FAIL and the parent repairs the proposal, resume the same verifier context against the revised exact candidate when the execution environment supports continuation. Do not start a fresh challenger cascade. If that verifier context becomes unavailable, treat the prior certification attempt as invalid and use only one replacement recovery verifier, with the replacement disclosed in the final readiness summary.

Metadata-only deterministic normalization that $to-tickets is already authorized to publish without substantive approval does not require this semantic verifier.

Required Dispatch Packet

The parent supplies a compact retrieval packet containing:

Source artifact: <durable identity>
Mode: fresh | remediation
Source state identity: <Spec Body Hash + Spec Contract Hash + root hashes or equivalent durable identities>
Parent TCM identity: <persisted pre-publication Spec Body Hash + Spec Contract Hash when a TCM exists>
Proposal identity: <sha256 of exact rendered proposal>
Exact proposed ticket bodies/actions: <complete candidate>
Parent coverage candidate: <exact rendered manifest/delta, including proposed Spec Body Hash + Spec Contract Hash when the TCM is part of substantive reconciliation>
Spec obligation routing: <IDs + dispositions>
Architecture/design source inventory: <durable source identities + anchors + dispositions>
Normative source-unit / ARCHSRC routing: <IDs + source anchors + dispositions>
Parent semantic-carry evidence: <compact rows/pointers>
Parent semantic-consumer impact evidence: <None | compact changed-invariant/consumer rows when remediation or changed authority makes it applicable>
Parent Context-Fit Manifest: <per-ticket scenario/domain/modality/proof-family summary + disposition>
Design-delegation result: <compact rows/pointers>

Read the full file on GitHub · 277 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. 10d ago Changed · +24 lines da5e3b2e19ce
  2. 20d ago Changed · +61 lines 653038480d3f
  3. 1mo ago Changed · +38 lines 68d9929b5378
  4. 1mo ago Changed · +7 lines 33acba257467
  5. 1mo ago First seen · 147 lines · 46 tokens per session scan A c1214541cf0e

Subscribe to this mod's changes

verify-ticket-decomposition is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 3,829 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-18.

Related

Other skills, from other repositories

tech-debt

Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.

Donchitos/Claude-Code-Game-Studios · 25 tokens

pr-review-triage

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

cobusgreyling/loop-engineering · 35 tokens

issue-creation

Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.

Gentleman-Programming/gentle-ai · 30 tokens

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

spec-kitty-runtime-review

Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…

Priivacy-ai/spec-kitty · 85 tokens

feature-dev

Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…

waybarrios/opencode-power-pack · 62 tokens