kana-review

kana-review is a skill for Claude Code from Linaqruf/kana-code-plugins. It costs 128 tokens per session (1,024 once invoked), scanned A, original, MIT.

A read-only second review of code, pull requests, plans, documents, proofs, or creative work. It checks claims against the repository and current web information, then reports findings without changing anything.

In plain words
What is it for?
Use it to review a change, design, plan, documentation, mathematical proof, or other content before approval.
Why use it?
It helps catch unsupported claims, missed problems, and bias from reviewing your own work. Tests and validators provide evidence for the findings.

Skill for Claude Code

Written for Claude Code: disallowed-tools in frontmatter. Also seen: mentions subagents; names the NotebookEdit tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kana-review plugin — 1 skill shipped together

Good fit Use it to review a change, design, plan, documentation, mathematical proof, or other content before approval.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add Linaqruf/kana-code-plugins
Claude Code
/plugin install kana-review

Made for: Claude Code.

Or install kana-review, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for kana-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/linaqruf/kana-code-plugins/kana-review/github.svg)](https://agentmods.dev/skills/linaqruf/kana-code-plugins/kana-review)
Your own site
<a href="https://agentmods.dev/skills/linaqruf/kana-code-plugins/kana-review"><img src="https://agentmods.dev/badge/skills/linaqruf/kana-code-plugins/kana-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.

agentmods 80×15 button for kana-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/linaqruf/kana-code-plugins/kana-review"><img src="https://agentmods.dev/badge/skills/linaqruf/kana-code-plugins/kana-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00128 $0.01024
Opus 5 $0.00064 $0.00512
Sonnet 5 $0.00026 $0.00205
Haiku 4.5 $0.00013 $0.00102

Measured 9d ago against content hash a2a1faaddcf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kana-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 9d 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.

plugins/kana-review/skills/kana-review/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kana-review

You are now an adversarial, read-only reviewer. You verify and report; you never fix. This skill runs inline in this session — there is no subagent, no packet ferry. Your independence comes from the user having opened a fresh session, not from isolation. The user watches every command you run.

1. Freshness check (first, always)

This review is trustworthy only if THIS session did not author the target. If your own conversation history shows you wrote or designed it, say so plainly and recommend the user run kana-review from a fresh session instead — then stop unless they explicitly say proceed. Self-review is the bias the whole method exists to avoid.

2. Load the contract

Read both, in full, before reviewing anything:

  • ${CLAUDE_PLUGIN_ROOT}/skills/kana-review/references/reviewer-contract.md — the constitution, grounding rules, evidence obligations, output format, approval standard. It governs everything below.
  • ${CLAUDE_PLUGIN_ROOT}/skills/kana-review/references/lenses.md — the domain lenses (code / plan / docs / math / content).

3. Resolve the target and lens

Input Resolution
PR number ("PR 42", "#42") gh pr view <N> for metadata/body; review pull/<N>/head (read-only fetch)
branch name diff vs the default branch
file path(s) the files as they stand
pasted artifact ("this chapter") the artifact in the conversation

Select the domain lens from the target type per lenses.md; the user may override ("…as plan", "content lens", "math"). Determine the phase: PLAN (a plan/design doc), IMPLEMENTATION (diff/PR/branch/files), or RE-REVIEW (prior findings exist).

4. Claims and prior findings — never rationale

  • Author claims: what the author asserts (PR body, commit messages, the user's summary), held as UNVERIFIED. Review what IS, not WHY they did it — rationale is not yours to weigh.
  • Prior findings (re-review): take them from the prior report the user pastes back, and apply the five dispositions with stable numbering.

Read the full file on GitHub · 91 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 91 lines · 128 tokens per session scan A a2a1faaddcf9

Subscribe to this mod's changes

kana-review is a skill published in the GitHub repository Linaqruf/kana-code-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 1,024 once invoked, about $0.0006 per session on Opus 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.

Related

Other skills, from other repositories

audit

Read-only quality gate that audits already-built work against its stated requirement and Definition of Done before it is allowed to move to 2done/. Produces a severity-ranked decision proposal (BLOCKER/MAJOR/MINOR/NIT) with evidence, never a fix. Use when an item is claimed complete, before moving anything to 2done/…

Marcel-Bich/marcel-bich-claude-marketplace · 129 tokens

pr-vetting

Use when the user wants to thoroughly investigate, vet, review, or security-scan a pull request before deciding how to handle it - especially PRs from external or unknown contributors. Runs a parallel multi-agent investigation (technical, security, value/fit, contributor reputation) and merges the findings into one…

Marcel-Bich/marcel-bich-claude-marketplace · 83 tokens

tuicr

Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.

agavra/tuicr · 50 tokens

liveagent-code-review

Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation. Use when the user asks for code review, invokes the Code Review action from Git Review, or explicitly mentions this skill.

Stack-Cairn/LiveAgent · 54 tokens

omh-image-cards

This is a Hermes-native img-summary workflow skill.

rlaope/oh-my-hermes · 66 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens