kumihimo-iteration

kumihimo-iteration is a skill for Claude Code from tzavislan/kumihimo. It costs 98 tokens per session (4,046 once invoked), scanned A, original, MIT.

A single-pass build skill for Kumihimo, a project that tracks development through a queue, plan, verification records, and commits. Each pass handles one queued item from start to finish.

In plain words
What is it for?
Taking the next queue item, implementing it, verifying it, recording the outcome, and making a local commit without publishing it.
Why use it?
It gives every change a repeatable process for selecting work, checking it against the plan, testing it, documenting the result, and leaving a clean repository.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run ruff format . >/dev/null && uv run ruff check . && uv run mypy && uv run pytest -q >/dev/null && uv run python tools/lint.py --fix >/dev/null && uv run p.

Good fit Taking the next queue item, implementing it, verifying it, recording the outcome, and making a local commit without publishing it.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tzavislan/kumihimo
agentmods
npx agentmods add skills/tzavislan/kumihimo/kumihimo-iteration

Made for: Claude Code.

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 kumihimo-iteration

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tzavislan/kumihimo/kumihimo-iteration"><img src="https://agentmods.dev/badge/skills/tzavislan/kumihimo/kumihimo-iteration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,046 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 $0.00098 $0.04046
Opus 5 $0.00049 $0.02023
Sonnet 5 $0.00020 $0.00809
Haiku 4.5 $0.00010 $0.00405

Measured 5d ago against content hash 7504c89da370, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kumihimo-iteration 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 5d 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.

.claude/skills/kumihimo-iteration/SKILL.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kumihimo iteration — one pass

One invocation is exactly one iteration: one queue item, one verdict, one commit, one journal entry. A loop re-invokes this skill for the next item. Every iteration must leave the repository committed and clean enough for the next one to start cold.

Working directory is C:\Kumihimo. Nothing outside it is written except Claude's own memory directory.

Before anything: the safety check

  1. Never git push. Commits are local. Pushing publishes to the public repo and triggers CI; it happens at milestone close with Thomas's say-so, or when he asks. If a milestone completes mid-loop, propose the push in the report and keep looping.
  2. Never publish to PyPI, create GitHub releases, or post anywhere.
  3. Never weaken an invariant in CLAUDE.md to make an item pass. If an item and an invariant collide, the item is needs-thomas.

Step 1 — Read the state

  • build/state/queue.md — the work, in order.
  • build/state/journal.md — what the last few iterations did.
  • build/state/loop.json — iteration counter and collision guard.

Collision guard. If loop.json has an active_session under 30 minutes old that is not this session, another loop is running — stop and say so. Otherwise claim it (session id + timestamp) and clear it when the iteration ends.

Step 2 — Pick exactly one item

Take the first item with status todo whose dependencies are all done. Do not batch. Do not skip ahead because something looks easier.

If an item is larger than one review round can hold, mark it split, write the smaller items beneath it, and take the first.

Stop conditions — end the loop, do not spin:

  • No todo items remain → say the queue is drained and stop.
  • Three consecutive iterations ended blocked → stop and report the pattern.
  • The same item has failed verification twice across two iterations → mark it needs-thomas, write why, and stop.
  • The clean tree fails uv run pytest -q before you changed anything → stop; the tree is broken and another iteration will not help.

Read the full file on GitHub · 312 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. 5d ago Changed · +86 lines 7504c89da370
  2. 9d ago First seen · 226 lines · 98 tokens per session scan A 3bdfe02a9ef5

Subscribe to this mod's changes

kumihimo-iteration is a skill published in the GitHub repository tzavislan/kumihimo (0 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 4,046 once invoked, about $0.0005 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

lean-commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes…

utk2103/Prompt-Studio · 80 tokens

git-helper

Generate git commit messages and help with git workflows.

maxvaega/skillkit · 12 tokens

safe-data-export

Use when a task's output is sensitive or large data and the destination is a path inside a version-controlled tree — writing the data is not the finish line, an unreviewed commit of it is the failure mode. Triggers on "export the data", "dump the DB", "extract observations", "write it to the repo", "save the logs"…

iamakbarsha1/whetstone · 94 tokens

tldr-commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /tldr-commit.…

0p9b/TLDR · 77 tokens

commit

Smart commit with Ollama-generated messages. Conventional commits, auto-push option. Triggers on: commit this, commit changes, smart commit, /commit.

chidekina/aria-superpowers · 34 tokens

contextual-commit

Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.

yamadashy/repomix · 62 tokens