Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add radumarias/xorio-claude-plugin/plugin install xorioWrote 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/radumarias/xorio-claude-plugin/review-loop)<a href="https://agentmods.dev/skills/radumarias/xorio-claude-plugin/review-loop"><img src="https://agentmods.dev/badge/skills/radumarias/xorio-claude-plugin/review-loop/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/radumarias/xorio-claude-plugin/review-loop"><img src="https://agentmods.dev/badge/skills/radumarias/xorio-claude-plugin/review-loop.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 | $0.00147 | $0.02476 |
| Opus 5.5 | $0.00059 | $0.00990 |
| Sonnet 5.5 | $0.00029 | $0.00495 |
| Haiku 4.5 | $0.00015 | $0.00248 |
Grade A, and why
review-loop 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-loop
A personal audit harness. Wraps /simplify + several reviewers + an adversarial-verify panel + a fix-applier into one looped workflow. The goal: catch real issues before push without ratholing on false positives.
Triggering
- Direct: user types
/review-loop(with optional args/flags below). - Inferred: user describes the use case ("review this branch before I push", "do a thorough audit on the last 5 commits", "run the full quality pass on the diff since Thursday"). Offer to invoke the skill; do not run it without confirmation if the diff is large (>50 files) since cost is non-trivial.
Args
/review-loop [scope] [flags...]
Scope (one of, optional — auto-detected if omitted):
origin/main..HEAD— any<ref>..<ref>rangeHEAD~N..HEAD— last N commitssince YYYY-MM-DD— commits since absolute datestaged/unstaged/working-tree— local diff against index/HEAD#NNN— fetch PR diff viagh pr diff NNN
Flags:
--push—git push origin <branch>after the loop (default: off; leave commits local)--remote— push branch, then schedule a one-shot remote CCR agent to run the audit in Anthropic's cloud; return the routine link and exit local session--strict— 4-lens verify with ≥3/4 majority; +1 to MAX_ROUNDS--skip-simplify— skip the/simplifycleanup phase--with-toolkit— also include/pr-review-toolkit:review-prin the finder panel (heavier; overlaps/code-review)--ultra— force every workflow agent onto the STRONG tier (the most capable Claude model currently available) regardless of session/effortsetting. Use when you want a heavyweight pass without flipping session state. Costs more.
Model tiers — resolve at runtime, never hardcode. This skill refers to model
tiers, not model names. STRONG = the most capable Claude model currently
available — identify it from the session environment (the system context names
the current flagship) and the Workflow tool's model options; never from this
file. workflow.js cannot read the environment itself, so when --ultra is
set, resolve STRONG before launching and pass it as
args.models = { strong: "<resolved alias>" }. If unresolved, the script
degrades to inheriting the session model. When a newer flagship ships, this
rule adopts it automatically.
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.
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 · 162 lines · 147 tokens per session scan A 07a846b2916b
review-loop is a skill published in the GitHub repository radumarias/xorio-claude-plugin (3 stars, last pushed 6d ago), licensed MIT. It adds 147 tokens to every session and 2,476 once invoked, about $0.0006 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…