kumihimo-retro

kumihimo-retro is a skill for Claude Code from tzavislan/kumihimo. It costs 69 tokens per session (686 once invoked), scanned A, original, MIT.

A scheduled review skill for Kumihimo, which folds lessons from the build journal into the project's agent instructions. It treats the journal as a record of what happened during development.

In plain words
What is it for?
Reviewing recent iterations, extracting lasting lessons, and updating the relevant skills, CLAUDE.md, or CONVENTIONS.md in one commit.
Why use it?
It prevents useful lessons from being forgotten and turns repeated mistakes or successful checks into rules for future work.

Skill for Claude Code

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

Good fit Reviewing recent iterations, extracting lasting lessons, and updating the relevant skills, CLAUDE.md, or CONVENTIONS.md in one commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tzavislan/kumihimo/kumihimo-retro
Install

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.

Any agent
npx skills add tzavislan/kumihimo --skill kumihimo-retro
Clone the repo
git clone --depth 1 https://github.com/tzavislan/kumihimo

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-retro

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tzavislan/kumihimo/kumihimo-retro"><img src="https://agentmods.dev/badge/skills/tzavislan/kumihimo/kumihimo-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 686 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 $0.00069 $0.00686
Opus 5 $0.00034 $0.00343
Sonnet 5 $0.00014 $0.00137
Haiku 4.5 $0.00007 $0.00069

Measured 10d ago against content hash 28730dcb08d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kumihimo-retro 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 10d 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-retro/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kumihimo retro — train the tooling

The iteration skill only stays good if what the loop learns gets written back into it. Yorishiro's build-iteration skill accreted its best rules (the blocking-rounds cap, the git add -A incident) from real failures; this skill makes that folding a scheduled obligation instead of an accident.

When

At each milestone close, or when loop.json's iteration is 10+ past last_retro_iteration — whichever comes first.

The pass

  1. Read build/state/journal.md from the entry after last_retro_iteration to now, plus any needs-thomas items in the queue.
  2. Extract durable lessons only. A lesson is durable when it would change what the next iteration does: a mistake made twice, a verification step that caught something (or failed to), a convention that turned out ambiguous, a command that should be in the battery. One-off trivia stays in the journal.
  3. Fold each lesson into the right home, smallest diff that carries it:
    • how to run an iteration → .claude/skills/kumihimo-iteration/SKILL.md
    • how to manage the project (status, queue, milestones, releases) → .claude/skills/kumihimo-manage/SKILL.md
    • a repo rule or invariant → CLAUDE.md
    • a coding/documentation rule → CONVENTIONS.md (and, if enforceable, queue a linter check for it — unenforced rules rot)
    • background Thomas should have across sessions → Claude's project memory
  4. Prune guidance that events proved wrong or stale. A skill that only grows becomes noise; deleting a dead rule is as valuable as adding a live one.
  5. Record: append a retro entry to the journal naming each lesson and where it landed (or why it was dropped), append a dated line to the Training log in .claude/skills/kumihimo-manage/SKILL.md (the unbroken log is the proof the loop is alive), set last_retro_iteration in loop.json, and commit everything as retro: <n> lessons through iteration <i>.

Read the full file on GitHub · 54 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. 10d ago First seen · 54 lines · 69 tokens per session scan A 28730dcb08d8

Subscribe to this mod's changes

kumihimo-retro is a skill published in the GitHub repository tzavislan/kumihimo (0 stars, last pushed 6d ago), licensed MIT. It adds 69 tokens to every session and 686 once invoked, about $0.0003 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.