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 di-sukharev/loop-code-review-skill --skill loop-code-reviewgit clone --depth 1 https://github.com/di-sukharev/loop-code-review-skillWrote 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/di-sukharev/loop-code-review-skill/loop-code-review)<a href="https://agentmods.dev/skills/di-sukharev/loop-code-review-skill/loop-code-review"><img src="https://agentmods.dev/badge/skills/di-sukharev/loop-code-review-skill/loop-code-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/di-sukharev/loop-code-review-skill/loop-code-review"><img src="https://agentmods.dev/badge/skills/di-sukharev/loop-code-review-skill/loop-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00792 |
| Opus 5.5 | $0.00017 | $0.00317 |
| Sonnet 5.5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
loop-code-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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow project rules. Use English with the sub-agents and the user's language with the user.
Scope and reviewer
In every round, review the full diff against HEAD and untracked files. Use a different scope when the user specifies one. Do not change staging.
Start each round with a fresh sub-agent that has no chat history. Give it the repository path, requirements, completion criteria, and the review criteria below. Do not pass author explanations, implementation plans, or earlier review findings and scores.
Follow the user's model and effort choices. Otherwise, choose by risk:
- For high-risk changes, use the strongest available Sol or Opus model at high effort. High risk includes stored data, migrations, security, concurrency, external contracts, and failures across multiple modules.
- For other changes, use a capable general model at medium effort.
Review loop
- Ask the reviewer to inspect the changes and affected code, then report without changing code. Each finding must include a location, a realistic failure scenario, its impact, and supporting evidence. State any assumptions. Also ask for an implementation score from 1 to 10 based on task fulfillment and material issues, with a short reason. Record each round's score.
- Accept findings for unmet requirements, bugs, regressions, data safety or security issues, build or deployment failures, material performance problems, and unnecessary migrations.
- Ask the same reviewer to fix only the accepted findings and run the relevant checks. Use the simplest sufficient fix and follow the testing rules below. Reuse project code and widely used, maintained libraries when they simplify an accepted fix. Use the project's ORM when it supports the operation. Use raw SQL only for a concrete functional or performance reason.
- After fixes, start another round to review the updated code. Stop when a round has no accepted findings and no material risk needs further review.
Use at most five rounds unless the user specifies another limit.
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.
- 7d ago Changed · -6 lines · +1 tokens per session 53ae684479a0
- 8d ago Changed 256f370dab1a
- 15d ago Changed · -55 lines d011130686ee
- 23d ago Changed 4ff2e80feb97
- 25d ago Changed · +24 lines · +16 tokens per session b44fbb3408bb
- 1mo ago Changed · +1 lines dfa4ae397694
- 1mo ago Changed · -34 lines · +2 tokens per session 1b62eb2fc2d5
- 1mo ago Changed · -23 lines · -17 tokens per session 152269ee7c3b
- 1mo ago Changed · -1 lines 9020e91f74e0
- 1mo ago First seen · 149 lines · 41 tokens per session scan A 050a397b8e9e
loop-code-review is a skill published in the GitHub repository di-sukharev/loop-code-review-skill (26 stars, last pushed 7d ago), licensed MIT. It adds 43 tokens to every session and 792 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 2026-08-30.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…