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 builtingit 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/builtin)<a href="https://agentmods.dev/skills/nexu-io/looper/builtin"><img src="https://agentmods.dev/badge/skills/nexu-io/looper/builtin/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/builtin"><img src="https://agentmods.dev/badge/skills/nexu-io/looper/builtin.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 | $0.00033 | $0.00585 |
| Opus 5.5 | $0.00013 | $0.00234 |
| Sonnet 5.5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
looper-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 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Looper review method
Read this file, then read every always-required referenced file below before reviewing. Read on-demand references only when their trigger matches the changed set.
Do not treat skill selection as a scope reduction: if no specialty skill matches, still complete the base review using this looper-review method. Apply the disposition schema, publish split, and repair-frontier contracts from the Looper reviewer prompt; this skill does not restate those execution contracts.
Procedure
- Understand stated intent from the PR seed, title/body, linked spec, and stated goals/non-goals.
- Enumerate in-scope changed files/ranges with local Git at the seeded base/head SHAs. Do not shrink that set because a specialty skill matches.
- Read the surrounding context needed to judge each change (callers, tests, contracts, lifecycle).
- For large PRs (roughly ≥15 changed files, or changes that cross packages), write an internal related-file plan grouping interface/impl/callers, db/readers, and prod/tests. Stay one reviewer; do not spawn sub-agents or subtasks.
- Establish concrete evidence for each independent in-scope finding: implementation trigger → code path → wrong consequence, or spec/docs section/omission → ambiguity or contradiction → implementation/validation consequence. Investigate uncertain candidates and omit unsupported claims from published findings. Group only the same root cause; keep unrelated concerns separate.
- Run a counterexample pass on those evidence-backed candidates in the same context before finalizing. The authority for dropping a candidate is that same review context (diff, callers, tests, contracts), not the agent's first structured finding list. Drop an evidence-backed candidate only when evidence proves it factually wrong or a same-root-cause duplicate. A missing reproduction is not disproof; static evidence can establish a finding.
- Deliver the existing disposition schema from the Looper prompt (
must_fix|follow_up|needs_human, severity, scopeBasis, scopeEvidence). Write comments that meet the quality bar in the reference files.
What ships with it
5 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 · 34 lines · 33 tokens per session scan A 35fcb9aa6208
looper-review is a skill published in the GitHub repository nexu-io/looper (136 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 585 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 2026-09-26.
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…