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 settings/ncaq/konoka/settingsgit clone --depth 1 https://github.com/ncaq/konokaGrade A, and why
konoka 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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$schema": "https://json.schemastore.org/claude-code-settings.json",
"extraKnownMarketplaces": {
"konoka": {
"source": {
"source": "github",
"repo": "ncaq/konoka"
}
}
},
"enabledPlugins": {
"kyosei@konoka": true,
"nix-tasuke@konoka": true,
"programming-tasuke@konoka": true,
"web-tasuke@konoka": true
},
"enableAllProjectMcpServers": true,
"permissions": {
"allow": [
"Bash(actionlint:*)",
"Bash(agnix:*)",
"Bash(deadnix:*)",
"Bash(editorconfig-checker:*)",
"Bash(gh * browse:*)",
"Bash(gh * checks:*)",
"Bash(gh * clone:*)",
"Bash(gh * diff:*)",
"Bash(gh * download:*)",
"Bash(gh * list:*)",
"Bash(gh * logs:*)",
"Bash(gh * search:*)",
"Bash(gh * status:*)",
"Bash(gh * verify:*)",
"Bash(gh * view:*)",
"Bash(gh * watch:*)",
"Bash(gh api *issues/*/comments*)",
"Bash(gh api *pulls/*/comments*)",
"Bash(gh api *pulls/*/reviews*)",
"Bash(gh browse:*)",
"Bash(gh search:*)",
"Bash(gh status:*)",
"Bash(git add:*)",
"Bash(git blame:*)",
"Bash(git branch:*)",
"Bash(git checkout:*)",
"Bash(git diff:*)",
"Bash(git fetch:*)",
"Bash(git log:*)",
"Bash(git ls-files:*)",
"Bash(git rev-parse:*)",
"Bash(git show:*)",
"Bash(git stash list:*)",
"Bash(git status:*)",
"Bash(git tag:*)",
"Bash(nix build:*)",
"Bash(nix develop:*)",
"Bash(nix eval:*)",
"Bash(nix flake:*)",
"Bash(nix fmt:*)",
"Bash(nix search:*)",
"Bash(nix-fast-build:*)",
"Bash(nixfmt:*)",
"Bash(npm ci:*)",
"Bash(npm exec --no:*)",
"Bash(npm run fix:*)",
"Bash(npm run lint:*)",
"Bash(npm test:*)",
"Bash(prettier:*)",
"Bash(shellcheck:*)",
"Bash(shfmt:*)",
"Bash(statix:*)",
"Bash(typos:*)",
"Bash(zizmor:*)",
"mcp__plugin_nix-tasuke_nixos"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.
- yesterday First seen · 88 lines scan A fa508be06500
konoka is a settings file published in the GitHub repository ncaq/konoka (3 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 settings, from other repositories
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.
electron
Agent settings declaring 17 allowed tools.
uv
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
ui-ux-pro-max-skill
Agent settings declaring 7 allowed tools.