Polaris: Skill for Claude Code

.agents/skills/review-spec-remediation/SKILL.md

review-spec-remediation is a skill for Claude Code, Codex from sponge-b0b/Polaris. It costs 43 tokens per session (2,743 once invoked), scanned A, original, Apache-2.0.

A follow-up process for handling confirmed problems found during a completed specification review. It records lasting root blockers—underlying conditions that prevent the specification from being correct—and prepares valid fixes for ticket creation.

In plain words
What is it for?
Use it after a specification review has produced a saved remediation packet. It checks that the reviewed code, branch, specification, and verification results are still current before updating remediation state.
Why use it?
It prevents stale review results or already-corrected issues from being acted on. It preserves blocker history while keeping only current, architecture-consistent remediation active.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. 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/review-spec-remediation/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 review-spec-remediation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/review-spec-remediation"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/review-spec-remediation.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 2,743 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 $0.02743
Opus 5 $0.00022 $0.01372
Sonnet 5 $0.00009 $0.00549
Haiku 4.5 $0.00004 $0.00274

Measured 6d ago against content hash e39e495103f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-spec-remediation 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 6d 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/review-spec-remediation/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Spec Remediation

$review-spec-remediation is invoked only by $review-spec after a current Pending Review Remediation packet is persisted.

It converts already validated review findings and scope corrections into durable remediation state.

It does not review source, create new findings, fix implementation, or independently change finding scope/axis authority.

Certified Domain Reconciliation Gate

This section is authoritative and supersedes preserved wording below that allows a later review to enlarge a previously certified semantic root/domain merely by labeling the new surface a root-definition gap or missed prior finding.

For every current Blocking finding mapped to a previously satisfied/closed root, the Pending packet must include one current $review-spec Domain Finality Reconciliation disposition:

Candidate: <finding/member>
Prior certified domain: <domain ID / durable certification reference>
Authority changed: yes | no
Membership under frozen predicate: in-domain | out-of-domain | ambiguous
Explicit authority contradiction: <None | exact source>
Finality disposition:
  in-domain-falsifier
  authority-changed-domain-stale
  closure-authority-defect
  domain-expansion

Consume that disposition mechanically:

  • in-domain-falsifier — eligible for ordinary current remediation reconciliation (missed prior finding or regression as provenance proves);
  • authority-changed-domain-stale — eligible only after the Pending packet identifies the actual changed authority and the current review rebuilt the affected domain from that new authority;
  • closure-authority-defectnot implementation remediation. Preserve the observation and halt the affected root/cell behind explicit authority/domain reconciliation; do not pass it to $to-tickets;
  • domain-expansion — non-actionable for the current certified domain. Preserve the observation historically but do not create/open a remediation cell or root from it.

A full fresh re-review, missing review-proof reuse ledger, stronger challenger, or broader plausible interpretation does not invalidate a certified closure domain by itself.

Read the full file on GitHub · 365 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. 6d ago Changed · +66 lines e39e495103f2
  2. 12d ago First seen · 299 lines · 43 tokens per session scan A 779c52a84c25

Subscribe to this mod's changes

review-spec-remediation 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 2,743 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.