Polaris: Skill for Claude Code

.agents/skills/architecture-remediation/SKILL.md

architecture-remediation is a skill for Claude Code, Codex from sponge-b0b/Polaris. It costs 44 tokens per session (7,332 once invoked), scanned A, original, Apache-2.0.

A routing workflow for architecture problems that stop another development workflow. It sends the unresolved issue back to the existing Wayfinder effort, which is the project's architecture-planning process.

In plain words
What is it for?
It helps capture architecture blockers, identify conflicts between governing sources, reopen the relevant architecture map, and hand the decision to the Wayfinder workflow. It does not implement the fix or change the specification itself.
Why use it?
It prevents an implementation or specification workflow from guessing at unresolved design decisions. It records each independent architecture decision as a ticket and preserves the evidence needed to route it.

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/architecture-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 architecture-remediation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/architecture-remediation"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/architecture-remediation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,332 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 $0.00044 $0.07332
Opus 5 $0.00022 $0.03666
Sonnet 5 $0.00009 $0.01466
Haiku 4.5 $0.00004 $0.00733

Measured 2d ago against content hash ce0df27bf2b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

architecture-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 2d 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/architecture-remediation/SKILL.md · 692 lines

How it starts

The opening of the file, as written. The whole thing — 692 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Remediation

Use when $implement-ticket, $review-spec, $to-remediation-specs, or another workflow cannot continue because of unresolved or incomplete architecture.

This workflow is governance-mode aware:

  • for a Wayfinder-managed Spec, it remains a routing workflow: recover the exact existing governor, reopen it when authoritative re-entry requires it, create/reuse decision work there, and hand resolution to $wayfinder;
  • for an intentionally Independent Spec, do not invent a Wayfinder merely to satisfy remediation. Resolve the bounded architecture decision in place with the owner, persist the resulting authority, amend the existing Spec, and return through $to-tickets before implementation resumes.

Never modify implementation here. Never create a new Wayfinder map for an Independent Spec solely because architecture remediation was required.

Session Independence

Assume no prior conversational or agent-session state.

Recover every correctness-critical input from the explicit invocation, repository, and durable tracker artifacts before acting. Prior-session summaries or remembered conclusions are routing context only and must not substitute for required durable evidence.

A blocker-driven Human Handoff must not depend on explanatory prose from the producing session. When the invoked source artifact has a durable <!-- architecture-blocker:v1 --> report, that report is the blocker authority for this remediation. A concise blocker summary in the invocation is supplemental only.

Independent-Spec owner-guided HITL may itself span multiple model/context sessions. Once that mode begins, the active <!-- independent-architecture-remediation-checkpoint:v1 --> on the remediation source artifact is the recoverable in-progress decision state. Owner answers, the semantic decision map, dependency/frontier state, and closure-discovered material choices must never exist only in agent context.

If required durable state cannot be recovered, report the missing artifact rather than infer or recreate it from memory.

Read the full file on GitHub · 692 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. 2d ago Changed · +370 lines · -3 tokens per session ce0df27bf2b9
  2. 11d ago First seen · 322 lines · 47 tokens per session scan A b70a4b853b0b

Subscribe to this mod's changes

architecture-remediation is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 7,332 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens