agentsclimarketplace

Efaimo

Skill efaimo-ai/efaimo

Audit what your agent loads: quality and context cost for MCP servers and Agent Skills

Install
npx -y skills add efaimo-ai/efaimo

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

2 things to look at

  • 21 days oldThe repository was created 21 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 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

Audit MCP servers and Agent Skills for quality and context-window cost. Use when the user wants to check an MCP server's token cost, lint a skill, verify 2026-07-28 MCP spec readiness, or add an efaimo badge or CI gate.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, 627 tokens by cl100k_base, as published. Nobody here has run it

efaimo

efaimo audits what an agent loads: the quality and context-window cost of MCP servers and Agent Skills. Reach for it when someone asks "how many tokens does this MCP server cost", "is my server ready for the 2026-07-28 MCP spec", "is this skill well-formed", or "add a CI gate / badge for context cost".

Commands

Run via npx efaimo (no install needed).

  • Weigh context cost of an MCP server npx efaimo weigh "npx -y <server-package>" for a stdio server, or npx efaimo weigh https://host/mcp for a remote one. Add --json for machine output, --badge badge.svg for a shields badge, --anthropic for Claude-exact token counts.
  • Weigh a skill or skill set npx efaimo weigh ./path/to/skill reports the metadata / body / referenced-file token split.
  • Weigh everything a client loads npx efaimo weigh --client claude-code (also claude-desktop, cursor, vscode) sums every configured server.
  • Audit an MCP server npx efaimo check --mcp "npx -y <server>" prints a quality grade plus a separate 2026-07-28 migration diff (what breaks under the stateless spec and how to fix it). Add --repo ./src to also scan source for deprecated primitives, --strict to fail on warnings.
  • Lint a skill npx efaimo check --skill ./skills/ validates frontmatter, trigger quality, context budget, file references, and injection patterns.
  • Gate a pull request on context cost Save a baseline with npx efaimo weigh "<server>" --out base.json, then in CI run npx efaimo weigh "<server>" --diff base.json --allow-increase 10 to fail when the tool-definition budget grows more than 10 percent.

Reading the output

Findings carry a stable rule id (E1xx MCP readiness, E12x-E13x MCP quality, S1xx skills) and a severity. The letter grade covers quality and skill findings only; 2026-07-28 readiness items appear separately as an ungraded migration diff. Token numbers are o200k estimates unless --anthropic is used; see the methodology doc for the full method.

Notes

efaimo is a linter and cost profiler, not a security scanner: its injection checks are surface heuristics. For supply-chain security use a dedicated scanner. Full rule reference: https://github.com/efaimo-ai/efaimo/blob/main/docs/RULES.md

What ships with it: 103 files

1081.9 KB alongside SKILL.md, 60 of them executable

assets/

docs/

examples/

research/

scripts/

63 more files not listed here. See all 103 in the repository.

Keep looking

Skills are one crate of 328,083. 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.