katamari: Skill for Claude Code

.agents/skills/katamari-review/SKILL.md

katamari-review is a skill for Claude Code, Codex from isamisushi/katamari. It costs 88 tokens per session (1,227 once invoked), scanned A, original, MIT.

A workflow for handling comments from a human reviewer in Katamari, a terminal tool that displays code changes and attaches comments to specific lines.

In plain words
What is it for?
Use it when responding to Katamari review feedback, especially when comments refer to particular files, lines, or changed sections.
Why use it?
It helps an agent find each open review comment, make the requested code change, and record that the comment has been handled.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is isamisushi/katamari's own configuration. It tells Claude Code and Codex how to work on katamari itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything katamari configures →

Reuse

Borrowing it

Nothing to install: this file belongs to isamisushi/katamari. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/isamisushi/katamari/main/.agents/skills/katamari-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/isamisushi/katamari

Made for: Claude Code, Codex.

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 katamari-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/isamisushi/katamari/katamari-review"><img src="https://agentmods.dev/badge/skills/isamisushi/katamari/katamari-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,227 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00088 $0.01227
Opus 5 $0.00044 $0.00613
Sonnet 5 $0.00018 $0.00245
Haiku 4.5 $0.00009 $0.00123

Measured 11d ago against content hash 0236503a8e45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

katamari-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 11d 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.

.agents/skills/katamari-review/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Addressing katamari review comments

katamari (ktmr) is a terminal diff-review tool. A human reviewer reads your diff inside ktmr diff, leaves comments anchored to specific file/line positions, and expects you to address each one and mark it resolved — this skill is that workflow.

Workflow

  1. List the open comments:

    ktmr comments list --json
    

    Each line is one JSON object:

    {"id": "a1b2c3d4", "created_at": 1700000000, "file": "src/lib.rs",
     "anchor": {"new_line": 42, "content_hash": ..., "context_hash": ...},
     "body": "this should handle the empty-input case too",
     "status": "open"}
    

    file is repo-relative; anchor.new_line is the 1-based line in the working tree version of that file at the moment the comment was written. Open the file and read that line (and its surroundings) to see what the comment is about — if the file has changed a lot since, the line number may no longer point at exactly the right spot; use judgment and the comment's own wording rather than trusting the number blindly. (katamari's own UI relocates comments live as the file changes; this CLI output always reports the comment's last known anchor.)

    A comment can also cover a contiguous range instead of one line: when that's the case, the object also has an end_anchor with the same shape as anchor, and the two together mean "every line from anchor.new_line to end_anchor.new_line, inclusive." Treat the comment as being about that whole range — read and address every line in it, not just the first one.

  2. For each open comment, make the requested change in the working tree.

  3. Mark it resolved:

    ktmr comments resolve <id>
    

    The reviewer's ktmr diff session picks this up live — no restart needed — and shows the comment as resolved (dimmed, struck through) at its current position in the diff.

  4. If a comment doesn't apply (already fixed, or you disagree with it), still resolve it rather than leaving it open silently, and say why in your own summary back to the reviewer.

Read the full file on GitHub · 109 lines

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. 11d ago First seen · 109 lines · 88 tokens per session scan A 0236503a8e45

Subscribe to this mod's changes

katamari-review is a skill published in the GitHub repository isamisushi/katamari (7 stars, last pushed 9d ago), licensed MIT. It adds 88 tokens to every session and 1,227 once invoked, about $0.0004 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

hunk-extensions

Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…

modem-dev/hunk · 105 tokens

hunk-launch-video

Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.

modem-dev/hunk · 60 tokens

hunk-release

Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.

modem-dev/hunk · 38 tokens

hunk-review

Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.

modem-dev/hunk · 69 tokens

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…

umputun/revdiff · 248 tokens

lightjj

Interacts with a running lightjj instance (browser-based Jujutsu/jj viewer) via the lightjj api CLI. Reads diffs, posts inline review comments, posts doc-mode suggestions, and steers the user's view. Use when the user has lightjj running and wants the agent to review changes, annotate diffs, or comment on markdown…

chronologos/lightjj · 77 tokens