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/kraulerson/solo-orchestrator/settingsgit clone --depth 1 https://github.com/kraulerson/solo-orchestratorWrote 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/kraulerson/solo-orchestrator/settings)<a href="https://agentmods.dev/settings/kraulerson/solo-orchestrator/settings"><img src="https://agentmods.dev/badge/settings/kraulerson/solo-orchestrator/settings.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
solo-orchestrator 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$comment": "BL-233 deliverable 8 — the MCP enforcement mechanism now fires in the framework repo itself, not only in the projects init.sh generates. Before this file existed, solo-orchestrator had no .claude/settings.json at all, so scripts/session-test-gate-check.sh, scripts/track-tool-usage.sh and scripts/session-mcp-gate.sh were wired into generated projects ONLY and none of it ran where the framework is actually built. The same gap still hides the version-check hook. The tracker is registered on BOTH post-tool events because a failed MCP call fires PostToolUseFailure and NOT PostToolUse (measured 2026-08-13); each registration passes its own --event so the tracker scores the outcome from the registration rather than guessing. BLAST RADIUS, stated rather than discovered: the PreToolUse entry BLOCKS Write and Edit until the required MCP tools have SUCCEEDED, and Qdrant is currently down (see BL-231), so this will block writes in this repo until the server is up. That is the intended posture — configured-but-unreachable blocks — and the honest way through is SOLO_MCP_ATTESTED=1 SOLO_MCP_REASON='<why>', which is recorded to .claude/process-state.json::mcp_attestations[] and refused if it cannot be written.",
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR\"/scripts/session-test-gate-check.sh"
}
]
}
],
"PostToolUse": [
{
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR\"/scripts/track-tool-usage.sh --event PostToolUse"
}
]
}
],
"PostToolUseFailure": [
{
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR\"/scripts/track-tool-usage.sh --event PostToolUseFailure"
}
]
}
],
"PreToolUse": [
{
"matcher": "Write",
What else settings.json configures
This page is one entry in a file that holds 5. 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.
- 4d ago First seen · 56 lines scan A 13e2d96d24b2
solo-orchestrator is a settings file published in the GitHub repository kraulerson/solo-orchestrator (27 stars, last pushed 8d ago), licensed MIT. 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 2026-08-30.
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).
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).