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.
curl -O https://raw.githubusercontent.com/sponge-b0b/Polaris/main/.agents/skills/improve-codebase-architecture/SKILL.mdgit clone --depth 1 https://github.com/sponge-b0b/PolarisWrote 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.
[](https://agentmods.dev/skills/sponge-b0b/polaris/improve-codebase-architecture)<a href="https://agentmods.dev/skills/sponge-b0b/polaris/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/improve-codebase-architecture/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.
<a href="https://agentmods.dev/skills/sponge-b0b/polaris/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/improve-codebase-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01521 |
| Opus 5.5 | $0.00012 | $0.00608 |
| Sonnet 5.5 | $0.00006 | $0.00304 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
improve-codebase-architecture 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
This skill is informed by the project's domain model and shared design vocabulary:
- Run
$codebase-designfor the architecture vocabulary (module, interface, depth, seam, adapter, leverage, locality) and its principles, including the deletion test, "the interface is the test surface," and "one adapter = hypothetical seam, two = real." Use those terms consistently in suggestions. - Use canonical domain language from
CONTEXT.md. - Treat accepted ADRs and applicable current architecture as constraints, not suggestions.
- If the Living Entity Wiki exists, consult relevant Strict Invariants, Rejected Approaches, Open Questions, and Planned entries before proposing changes.
- If authoritative sources materially disagree, surface
[source-conflict]rather than designing around one side.
1. Explore
Scope before scanning — YAGNI.
Deepening pays off when it makes recurring future changes easier, so prioritize areas that actually matter.
- If the user names a module, subsystem, or pain point, use that scope.
- Otherwise inspect enough Git history to identify recurring hot spots. If changes are scattered, widen the search deliberately.
Read the relevant CONTEXT.md, accepted ADRs, and current architecture docs first.
If the Living Entity Wiki exists, use wiki/index.md to locate the relevant entity page(s). This is a read-only consultation, not a $wiki-sync invocation.
Then explore using the project's repository-analysis tools such as $repowise, $codegraph, $codebase-memory-mcp, or $graphify.
Look organically for friction:
- Where does understanding one concept require bouncing between many modules?
- Where are modules shallow — interface nearly as complex as implementation?
- Where were functions extracted mainly for testability while the real bugs live in their composition?
- Where is locality poor?
- Where do supposedly separate modules leak knowledge across their seams?
- Which behavior is hard to test through its real interface?
What ships with it
2 files 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.
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.
- 1mo ago First seen · 175 lines · 31 tokens per session scan A 43fdf3614917
improve-codebase-architecture is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,521 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…