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.
npx skills add tzavislan/kumihimo --skill kumihimo-managegit clone --depth 1 https://github.com/tzavislan/kumihimoWrote 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/skills/tzavislan/kumihimo/kumihimo-manage)<a href="https://agentmods.dev/skills/tzavislan/kumihimo/kumihimo-manage"><img src="https://agentmods.dev/badge/skills/tzavislan/kumihimo/kumihimo-manage/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/skills/tzavislan/kumihimo/kumihimo-manage"><img src="https://agentmods.dev/badge/skills/tzavislan/kumihimo/kumihimo-manage.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 | $0.00000 | $0.03002 |
| Opus 5 | $0.00000 | $0.01501 |
| Sonnet 5 | $0.00000 | $0.00600 |
| Haiku 4.5 | $0.00000 | $0.00300 |
Grade A, and why
kumihimo-manage 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kumihimo manage — run the project
The umbrella over the other two skills: /kumihimo-iteration builds one queue
item; /kumihimo-retro folds lessons back into the skills; this one is
everything else a maintainer does. Working directory C:\Kumihimo. The
standing rules in CLAUDE.md bind here too: milestone-close pushes carry
Thomas's standing say-so (2026-08-24); everything else outward — off-cycle
pushes, publishing, releasing — still needs his explicit yes and this skill
only prepares it.
Orient (always first)
Read, in order: CLAUDE.md → build/state/queue.md → build/state/journal.md
(last few entries) → build/state/loop.json → git log --oneline | head and
git status --short. PLAN.md section references in queue items are the design
authority for anything deeper.
Status report
When asked where things stand, answer from evidence, not memory: milestone progress from the queue (done/todo per M-block), last journal entry's verified state, whether the tree is clean and the battery green (run it if the answer matters), and what the next eligible queue item is. One tight paragraph plus the next action.
Groom the queue
- Split coarse items (one PLAN.md milestone bullet each) into iteration-sized items before their milestone starts — an item is right- sized when one review round holds the whole diff.
- Write discovered work down with a
needs:line and the PLAN.md section it serves; never let it live only in a chat. - The queue item is the acceptance authority. Roadmap nodes carry a summary that points at the queue id; when plan prose, roadmap, and queue disagree, the queue wins and the others get corrected in the same pass (the K20 halo collision is the standing example).
- Anything needing a decision Thomas hasn't made: status
needs-thomas, the question stated plainly, and surface it in the next report.
Build
Dispatch /kumihimo-iteration for one item; suggest wrapping it in /loop
when Thomas wants unattended progress. Do not inline a build pass here — the
iteration skill owns its own safety and verification rules.
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.
- 8d ago Changed · +63 lines 760f6b67c4aa
- 11d ago First seen · 144 lines · 0 tokens per session scan A 0cbebc37dc30
kumihimo-manage is a skill published in the GitHub repository tzavislan/kumihimo (0 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,002 tokens. 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 skills, from other repositories
worktree-execution
Creates, pins, and cleans isolated Git worktree pairs for comparison trials. Use only when a Rashomon prompt or skill evaluation needs paired execution environments or orphan recovery.
release-checklist
Minimal release checklist used as the control variant.
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…
lfe-archivist
Act as the Archivist for an LFE-compliant project. Use when a change is approved and needs documentation sync, changelog updates, or pipeline status cleanup.
git-helper
Generate git commit messages and help with git workflows.
publish-oss-repo
Use when preparing a repository for public release, or auditing one that already has working code but still reads as neglected to a stranger or to GitHub's own UI — "has the files" is not "reads as maintained". Triggers on "publish a repo", "open source this", "release", "make it look maintained", "license shows…