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/buildonspark/spark/settingsgit clone --depth 1 https://github.com/buildonspark/sparkWrote 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/settings/buildonspark/spark/settings)<a href="https://agentmods.dev/settings/buildonspark/spark/settings"><img src="https://agentmods.dev/badge/settings/buildonspark/spark/settings.svg" alt="Measured on agentmods" height="20"></a>Grade B, and why
spark scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
"Bash(python3 -m json.tool:*)", How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"plansDirectory": ".claude/plans",
"permissions": {
"allow": [
"Bash(git status:*)",
"Bash(git log:*)",
"Bash(git diff:*)",
"Bash(git show:*)",
"Bash(git branch:*)",
"Bash(git remote:*)",
"Bash(git fetch:*)",
"Bash(git rev-parse:*)",
"Bash(git ls-files:*)",
"Bash(git ls-tree:*)",
"Bash(git ls-remote:*)",
"Bash(git blame:*)",
"Bash(git grep:*)",
"Bash(git describe:*)",
"Bash(git reflog:*)",
"Bash(git tag:*)",
"Bash(git stash list:*)",
"Bash(git config --get:*)",
"Bash(git config --list:*)",
"Bash(git merge-base:*)",
"Bash(git shortlog:*)",
"Bash(git name-rev:*)",
"Bash(git cat-file:*)",
"Bash(git add:*)",
"Bash(git checkout:*)",
"Bash(git worktree:*)",
"Bash(git --version:*)",
"Bash(git help:*)",
"Bash(git check-ignore:*)",
"Bash(git -C * status:*)",
"Bash(git -C * log:*)",
"Bash(git -C * diff:*)",
"Bash(git -C * show:*)",
"Bash(git -C * branch:*)",
"Bash(git -C * remote:*)",
"Bash(git -C * fetch:*)",
"Bash(git -C * rev-parse:*)",
"Bash(git -C * ls-files:*)",
"Bash(git -C * ls-tree:*)",
"Bash(git -C * ls-remote:*)",
"Bash(git -C * blame:*)",
"Bash(git -C * grep:*)",
"Bash(git -C * describe:*)",
"Bash(git -C * reflog:*)",
"Bash(git -C * tag:*)",
"Bash(git -C * stash list:*)",
"Bash(git -C * config --get:*)",
"Bash(git -C * config --list:*)",
"Bash(git -C * merge-base:*)",
"Bash(git -C * shortlog:*)",
"Bash(git -C * name-rev:*)",
"Bash(git -C * cat-file:*)",
"Bash(git -C * add:*)",
"Bash(git -C * checkout:*)",
"Bash(git -C * worktree:*)",
"Bash(git -C * check-ignore:*)",
"Bash(gh pr list:*)",
"Bash(gh pr view:*)",
"Bash(gh pr diff:*)",
"Bash(gh pr checks:*)",
"Bash(gh pr status:*)",
"Bash(gh What else settings.json configures
This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.
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 · 214 lines scan B 8dd02e1dd5e5
spark is a settings file published in the GitHub repository buildonspark/spark (110 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 B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other settings, from other repositories
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
superset
Agent settings declaring 1 hook event (PreToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
RuView
Agent settings declaring 8 hook events (PreToolUse, PostToolUse, UserPromptSubmit, SessionStart) and 4 allowed tools.
orm
Agent settings declaring 4 hook events (PreToolUse, PostToolUse, WorktreeCreate, Stop) and 21 allowed tools.
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.