agentsclimarketplace

Momo tools

Skill jordannn02/momo-tools/plugin/skills/momo-tools

Local-first capability router and safety gate for AI agent tools

Install
npx -y skills add jordannn02/momo-tools --skill momo-tools

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Route an AI agent task through a local capability index, risk gates, action gates, and verification levels before choosing tools. Use when the user asks which tool/skill/plugin/connector/script to use, wants a capability dashboard, or needs a safe workflow for work that could touch files, private data, credentials, external services, browser state, automation, or persistence.

SKILL.md

2.3 KB, 428 tokens by cl100k_base, as published. Nobody here has run it

MoMo_tools

MoMo_tools is a local-first capability router. It helps an agent choose the smallest safe capability set instead of exposing every available tool.

Use When

  • The user asks which tool, skill, plugin, connector, or script should be used.
  • A task could involve writes, saves, private data, credentials, external network calls, browser/local app state, scheduled automation, or destructive operations.
  • The user asks for a dashboard or audit of available capabilities.
  • A workflow should distinguish installed/configured tools from verified tools.

Core Rule

Do not treat a capability as safe or working just because it is registered.

Respect verification_level:

  • visible: discoverable only.
  • executed: ran once on a bounded task with evidence.
  • verified-working: repeatable evidence and risk boundary documented.

Suggested Commands

./plugin/scripts/momo-tools validate
./plugin/scripts/momo-tools dashboard
./plugin/scripts/momo-tools route --prompt "Summarize this PDF, do not save anything"
./plugin/scripts/momo-tools benchmark
./plugin/scripts/momo-tools evidence
./plugin/scripts/momo-tools pressure
./plugin/scripts/momo-tools doctor --as-of 2026-07-10T12:00:00+00:00
./plugin/scripts/momo-tools repair-plan --dry-run --as-of 2026-07-10T12:00:00+00:00
./plugin/scripts/momo-tools test

Safety

Routing is advisory. The agent must still obey user constraints, approval gates, and host application safety rules.

MoMo_tools validation, benchmark, evidence, pressure, doctor, and repair-plan checks should not call real connectors, access browser profiles, read secrets, or mutate production systems.

Run strict doctor from a source checkout with an explicit independent --installed-root. Non-strict doctor is diagnostic. repair-plan requires --dry-run, has no apply mode, and must leave applied=false with write_operations_executed=0.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most automation workflows skills give in 428 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

  • Write conventional commit messagesin 36 of 745, across 35 files
  • Delete branches after mergein 30 of 745, across 21 files
  • Make atomic commitsin 25 of 745, across 15 files
  • Write minimal code to pass testsin 22 of 745, across 10 files
  • Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
  • Use try-catch for error handlingin 20 of 745, across 8 files
  • Run tests before committingin 20 of 745, across 12 files
  • Write tests before implementationin 20 of 745, across 8 files
  • Configure branch protection rulesin 19 of 745, across 5 files
  • Explain the why in commit messagesin 19 of 745, across 9 files
  • Refactor code while tests remain greenin 19 of 745, across 6 files
  • Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

  • do not treat a registered capability as automatically safe
  • respect the verification level assigned to a capability
  • distinguish discoverable capabilities from verified ones
  • obey user constraints and host application safety rules
  • run strict doctor from a source checkout with an explicit independent installed-root
  • require dry-run mode for repair-plan

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.