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 agentmods add instructions/linaqruf/kana-code-plugins/claude-mdgit clone --depth 1 https://github.com/Linaqruf/kana-code-pluginsWrote 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/linaqruf/kana-code-plugins/claude-md)<a href="https://agentmods.dev/instructions/linaqruf/kana-code-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/linaqruf/kana-code-plugins/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 | $0.01541 | $0.01541 |
| Opus 5 | $0.00771 | $0.00771 |
| Sonnet 5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
kana-code-plugins 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 3d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kana-code-plugins — maintainer instructions
Claude Code plugin marketplace (5 plugins under plugins/, manifest at
.claude-plugin/marketplace.json). These rules are incident-proven — each one
exists because its violation shipped or nearly shipped a bug.
Hard rules
- plugin.json and marketplace.json stay byte-identical on
versionANDdescriptionfor every plugin. Compare programmatically (-ceq), don't eyeball. They have drifted before. - Ship-verification runs against the COMMITTED tree, never the working
tree:
git cat-file -e HEAD:<path>for must-exist files, andgit archive HEAD→ temp dir →claude plugin validate(+ marketplace--strict) before any push. A working-tree validate once passed while the entry-point file was silently gitignored out of the commit (PR #35), and a clean-export validate caught broken agent frontmatter (PR #36). - The root
.gitignorespec rules (/SPEC.md,/SPEC/,/spec/,/specs/,/prompt.md,/dev/) are root-anchored ON PURPOSE — never widen them back to**/patterns. Unanchored patterns match every directory, case-insensitively on Windows, and silently swallowed plugin source once. Corollary: rootSPEC.md/prompt.mdare RESERVED, ignored output slots for kana-spec runs on this repo — never commit tracked files at those paths. A kana-spec run here may also offer to UPDATE rootCLAUDE.md— this maintainer file, which IS tracked — so review that diff before accepting. docs/is local-only (listed in.git/info/exclude) — design docs and review logs live there and are never committed.- Validation gates before any plugin PR:
claude plugin validate <plugin-dir>andclaude plugin validate .claude-plugin/marketplace.json --strictmust pass clean — from the clean export per rule 2. Agent/skill frontmatter is YAML: an unquoted:inside a description silently drops ALL frontmatter at runtime; use folded block scalars (>-) for long descriptions. - Stage by exact path (
git add plugins/<name> .claude-plugin/...) — nevergit add -A/commit -a. Unrelated working-tree state must not ride along in a plugin PR.
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.
- 3d ago First seen · 104 lines · 1,541 tokens per session scan A 55f4e332ce94
kana-code-plugins CLAUDE.md is an instructions file published in the GitHub repository Linaqruf/kana-code-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,541 tokens to every session, about $0.0077 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
fakoli-plugins CLAUDE.md
Claude Code instructions for fakoli/fakoli-plugins, covering claude.md, project overview, key commands, plugin validation and registry generation.
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).
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.
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.
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.
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).