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 commands/utensils/mcp-nixos/test-toolsgit clone --depth 1 https://github.com/utensils/mcp-nixosWrote 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/commands/utensils/mcp-nixos/test-tools)<a href="https://agentmods.dev/commands/utensils/mcp-nixos/test-tools"><img src="https://agentmods.dev/badge/commands/utensils/mcp-nixos/test-tools.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 | $0.00009 | $0.04389 |
| Opus 5 | $0.00005 | $0.02194 |
| Sonnet 5 | $0.00002 | $0.00878 |
| Haiku 4.5 | $0.00001 | $0.00439 |
Grade A, and why
test-tools 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 today.
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 — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test MCP NixOS Tools
CRITICAL INSTRUCTIONS:
- You MUST dispatch ALL test groups below to subagents running IN PARALLEL
- Each subagent MUST run EVERY test in its assigned group - no skipping
- After ALL subagents complete, compile a SINGLE summary table with pass/fail for EVERY test
- Do NOT stop early - all 8 test groups must be executed
Dispatch Strategy
Launch these 8 subagents IN PARALLEL (single message with multiple Task tool calls):
Group 1: Core NixOS Source Tests
Subagent prompt:
Test the mcp__nixos__nix tool for the core NixOS source. Run EVERY test below and record pass/fail:
SEARCH:
- action=search, source=nixos, type=packages, query=firefox
- action=search, source=nixos, type=options, query=nginx
- action=search, source=nixos, type=programs, query=vim, limit=3
- action=search, source=nixos, channel=stable, query=firefox, limit=3
- action=search, source=nixos, query=xyznonexistent12345 (expect "No packages found")
DOTTED/NAMESPACED PACKAGE SEARCH (issue #118 regression):
- action=search, source=nixos, type=packages, query=kdePackages.qt6ct (expect results containing qt6ct)
- action=search, source=nixos, type=packages, query=python314Packages.matplotlib (expect results containing matplotlib)
- action=search, source=nixos, type=packages, query=rocmPackages.clang (expect results containing clang)
- action=search, source=nixos, type=packages, query=llvmPackages_22.systemLibcxxClang (expect results; may match clang variants)
- action=search, source=nixos, type=packages, query=flang (expect exact match - control test)
INFO:
- action=info, source=nixos, type=package, query=firefox
- action=info, source=nixos, type=option, query=services.nginx.enable
- action=info, source=nixos, query=nonexistentpkg123 (expect NOT_FOUND)
- action=info, source=nixos, type=package, query=kdePackages.qt6ct (issue #118: should find qt6ct via attr path)
- action=info, source=nixos, type=package, query=qt6ct (should show attribute path in output)
STATS:
- action=stats, source=nixos
CHANNELS:
- action=channels
Return a markdown table with Test | Expected | Actual | Status (PASS/FAIL) for each test.
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.
- today Changed 567b4373389b
- 6d ago First seen · 435 lines · 9 tokens per session scan A 5baa32ef0a5b
test-tools is a command published in the GitHub repository utensils/mcp-nixos (823 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 4,389 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
checkpoint
Write a new link in the continuum chain summarizing decisions/changes since the last link.
dream
Roll up the last N links into a single phase-digest link; originals move to archived/ (never deleted).
review-session
Arm-2 — critique the current/last session for efficiency & quality, emit a Zone-A distillation, offer a deliberate GitHub feedback report.
telemetry
Inspect, opt in/out of, and audit mochi's anonymous usage telemetry.
insights
Owner-only — fetch and print the mochi-insight server's aggregate summary.
render
Inspect an archived transcript (gzipped) — show counts, tool calls, errors. Useful after a PreCompact or SessionEnd, before deciding to write a retroactive /continuum:checkpoint.