Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nexu-io/looper --skill maintainability-reviewgit clone --depth 1 https://github.com/nexu-io/looperWrote 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/nexu-io/looper/maintainability-review)<a href="https://agentmods.dev/skills/nexu-io/looper/maintainability-review"><img src="https://agentmods.dev/badge/skills/nexu-io/looper/maintainability-review/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/nexu-io/looper/maintainability-review"><img src="https://agentmods.dev/badge/skills/nexu-io/looper/maintainability-review.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 | $0.00044 | $0.00998 |
| Opus 5.5 | $0.00018 | $0.00399 |
| Sonnet 5.5 | $0.00009 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
maintainability-review 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainability review
Read this method and the examples before reviewing. Follow the existing Looper prompt's output, publication, scope, and repair-frontier contracts. This method adds no output fields, tool requirements, agents, or publish permissions.
Boundaries
- Keep the full base correctness review. On the first pass, cover all in-scope changes, not just code that looks repetitive or long.
- On re-review, check existing findings, new commits, and directly affected code. Do not restart a refactoring audit of unchanged historical code.
- The agent's structured findings are the review conclusions; repository rules and PR intent supply their basis. Infrastructure signals do not decide whether a semantic concern is valid.
- Prefer reuse, consolidation, or deletion over a new abstraction. Reducing lines or increasing reuse is not a goal by itself.
Investigation
-
Read PR goals/non-goals, linked requirements, and repository rules. Identify the changed behavior and its intended boundaries.
-
Inspect changed code plus relevant existing implementations, callers, and tests. Search for the same business invariant, not just matching text. State the limits of the search: failure to find a reusable helper does not prove none exists.
-
Examine these dimensions, with their counterexamples:
Dimension Investigate Do not report merely because Duplicated logic Multiple implementations of one rule that must evolve together Similar text exists with different semantics Existing capability An applicable helper/component/service already implements the new behavior A helper has a similar name but different permissions, transactions, errors, or dependencies Responsibilities Independent duties make understanding, modification, or testing concretely harder A cohesive declaration, rule table, sequential protocol, or explicit test is long Complexity State, branches, wrappers, or forwarding layers can be removed without changing behavior A layer performs necessary authorization, compatibility, retries, or resource management Abstraction boundaries One shared invariant is scattered, or different rules are forced into one abstraction A repetition count, implementation count, or line threshold has been reached Test maintainability Repeated setup forks an invariant, or parameterization hides scenarios, assertions, and failure causes Independent tests could be shorter at the cost of diagnosis
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.
- today First seen · 54 lines · 44 tokens per session scan A 7a8c4771240f
maintainability-review is a skill published in the GitHub repository nexu-io/looper (136 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 998 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 2026-10-29.
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"…
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…
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…
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…