Borrowing it
Nothing to install: this file belongs to tzavislan/kumihimo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tzavislan/kumihimo/main/CLAUDE.mdgit 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/instructions/tzavislan/kumihimo/claude-md)<a href="https://agentmods.dev/instructions/tzavislan/kumihimo/claude-md"><img src="https://agentmods.dev/badge/instructions/tzavislan/kumihimo/claude-md.svg" alt="Measured on agentmods" 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 | $0.00900 | $0.00900 |
| Opus 5 | $0.00450 | $0.00450 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
kumihimo CLAUDE.md 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Kumihimo
Agent context for this repository. Read this, then PLAN2.md — the v0.2 design authority (approved 2026-08-24; PLAN.md is the v0.1 record). Deviations from the plan are recorded in build/state/journal.md, never silently.
Running the project?
/kumihimo-manage is the umbrella
— status, queue grooming, milestone close, release prep — and carries the
Training log. The work queue is build/state/queue.md,
one build pass is
/kumihimo-iteration, and
lessons fold back into all three skills via
/kumihimo-retro at each milestone
close.
Invariants — do not violate
- Everything goes through
core.ops. CLI, HTTP, and MCP are thin clients. If a mutation path bypasses the ops layer, it is a bug even when it works. - Files are the only truth. An op succeeds when the bytes are on disk. The editor holds no unsaved semantic state; git is the undo.
core/andcompile/import no client code — enforced bytests/test_boundaries.py.- Deterministic braid. Same plan → byte-identical prompt, on every OS. Golden tests guard it; nondeterminism is a bug where it becomes observable.
- No network, no LLM calls, no telemetry in the library. Ever.
format: 1is versioned. Format changes ship with a migration command.- Round-trip fidelity is data integrity. A node file the user wrote must survive load→save byte-for-byte unless the operation is an edit to it. "Kumihimo reformatted my file" is treated as data loss.
Rules of the repo
- Git stays current: push at every milestone close (standing say-so, Thomas 2026-08-24) — the public repo reflects each upgrade. Off-cycle pushes still need his explicit yes; never push mid-iteration. A red CI after a push is the top of the queue until green.
- Documentation ships with the change, not after (Thomas, 2026-08-24).
An item that changes user-visible behavior updates its docs-site page in
the same commit; UI-pixel changes re-shoot screenshots
(
tools/screenshots.py) at milestone close; changed README commands get re-verified on a clean checkout. CI's strict docs build gates the rest. - Never publish to PyPI — release is Thomas's act, via the tagged release workflow.
- Coding rules are CONVENTIONS.md and they are enforced:
uv run python tools/lint.py(add--fixto regenerate README indexes). - Full local check, in CI's order:
uv run ruff check . ; uv run ruff format --check . ; uv run mypy ; uv run pytest -q ; uv run python tools/lint.py - Prompt-effectiveness claims follow the verification bar in CONVENTIONS.md — say "not verified" unless a braid was actually run against a real agent.
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.
- 6d ago First seen · 61 lines · 900 tokens per session scan A 44ad2f1c3bec
kumihimo CLAUDE.md is an instructions file published in the GitHub repository tzavislan/kumihimo (0 stars, last pushed 3d ago), licensed MIT. It adds 900 tokens to every session, about $0.0045 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.