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.
git clone --depth 1 https://github.com/ypolon7kiy/akashiWrote 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/rules/ypolon7kiy/akashi/code-review-agent)<a href="https://agentmods.dev/rules/ypolon7kiy/akashi/code-review-agent"><img src="https://agentmods.dev/badge/rules/ypolon7kiy/akashi/code-review-agent/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/rules/ypolon7kiy/akashi/code-review-agent"><img src="https://agentmods.dev/badge/rules/ypolon7kiy/akashi/code-review-agent.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 | $0.00016 | $0.00374 |
| Opus 5.5 | $0.00006 | $0.00150 |
| Sonnet 5.5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
code-review-agent 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.
What it actually says
Akashi code review (global)
The code review agent instructions for this project are maintained in your global Cursor user configuration, not duplicated here.
Where to find them
- On this machine:
~/.cursor/rules/code-review-agent.mdc(same content as the former project rule). - Cursor UI: Cursor Settings → Rules, Commands → User rules — if your build does not load
~/.cursor/rulesautomatically, open that file and paste or sync its body into a User rule so Agent (Chat) picks it up everywhere.
Scope: The global rule has no file globs; Cursor applies it when Agent judges it relevant from the description, or when you @mention it. If you want it tied to src/** in this repo only, duplicate or symlink a project rule with globs under .cursor/rules.
For collaborators: add the same user rule (or keep a copy under .cursor/rules in the repo) so reviews stay consistent.
TypeScript: imports at the top
- All static
import/import typedeclarations belong at the top of the file (before any other statements). No mid-file imports. - Prefer top-level
import type { … } from "…"over inlineimport("…").Typein type positions when it expresses the same dependency. - Use dynamic
import()only for real lazy-loading of runtime modules, not as a substitute for organizing type imports.
The same bullets are mirrored in the global user rule ~/.cursor/rules/code-review-agent.mdc under Code quality and Common issues.
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 · 27 lines · 16 tokens per session scan A a1b0069001bd
code-review-agent is a cursor rule published in the GitHub repository ypolon7kiy/akashi (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 374 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 cursor rules, from other repositories
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.