skillgrade-setup

A guide for setting up and running evaluations for agent skills. An evaluation runs defined tasks against a skill and scores the results.

In plain words
What is it for?
It is used to install the evaluation tool, create an eval.yaml file, define tasks and workspaces, configure graders, and run trials.
Why use it?
It provides a consistent way to test whether a skill works across tasks instead of relying on one manual check.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/mgechev/skillgrade/skillgrade-setup
Any agent
npx skills add mgechev/skillgrade --skill skillgrade-setup
Clone the repo
git clone --depth 1 https://github.com/mgechev/skillgrade

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 928 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00928
Opus 5 $0.00026 $0.00464
Sonnet 5 $0.00010 $0.00186
Haiku 4.5 $0.00005 $0.00093

Measured 2d ago against content hash 03b5d27752ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillgrade-setup 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 2d 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.

skills/skillgrade-setup/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skillgrade Evaluation Setup

Procedures

Step 1: Install Skillgrade

  1. Verify Node.js 20+ and Docker are available.
  2. Run npm i -g skillgrade to install the CLI globally.

Step 2: Initialize an Eval Configuration

  1. Navigate to the skill directory (must contain a SKILL.md).
  2. Set the appropriate API key environment variable (GEMINI_API_KEY, ANTHROPIC_API_KEY, or OPENAI_API_KEY).
  3. Run skillgrade init to generate an eval.yaml with AI-powered tasks and graders.
  4. If an eval.yaml already exists, pass --force to overwrite: skillgrade init --force.
  5. Without an API key, a well-commented template is generated instead.

Step 3: Configure eval.yaml

  1. Read references/eval-yaml-spec.md for the full configuration schema.
  2. Define one or more tasks under the tasks: key. Each task requires:
    • name: unique task identifier
    • instruction: what the agent should accomplish
    • workspace: files to copy into the evaluation container
    • graders: one or more scoring mechanisms (see the skillgrade-graders skill)
  3. Optionally configure defaults: for agent, provider, trials, timeout, and threshold.

Step 4: Run Evaluations

  1. Select an appropriate preset based on the evaluation goal:
    • --smoke (5 trials): Quick capability check.
    • --reliable (15 trials): Reliable pass rate estimate.
    • --regression (30 trials): High-confidence regression detection.
  2. Run the evaluation: skillgrade --smoke.
  3. Run a specific eval by name: skillgrade --eval=fix-linting.
  4. Run multiple evals: skillgrade --eval=fix-linting,write-tests.
  5. Run only deterministic graders (skip LLM calls): skillgrade --grader=deterministic.
  6. Run only LLM rubric graders: skillgrade --grader=llm_rubric.
  7. The agent is auto-detected from the API key. Override with --agent=gemini|claude|codex|acp|opencode|command.
  8. For ACP, pass --acp-command="gemini --acp" or set defaults.acp.command.
  9. For OpenCode, pass --opencode-agent=build|plan|explore or --opencode-model=provider/model.
  10. For a custom agent, pass --agent=command --command="node mycli.js" or set defaults.command. The instruction is piped to the command's stdin.
  11. Override the provider with --provider=docker|local.

Read the full file on GitHub · 61 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 61 lines · 52 tokens per session scan A 03b5d27752ad

Subscribe to this mod's changes

skillgrade-setup is a skill published in the GitHub repository mgechev/skillgrade (696 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 928 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

self-nudge-loop

Build a reactive same-session autonomy loop using KiroCrew's AutoNudgeService. One long-lived dashboard session keeps working toward a goal — when its turn completes and no user input arrives within idlesecs, the service auto-injects a nudge message into the SAME session. Survives tab close, logout, and gateway…

kirodotdev/KiroCrew · 131 tokens

skill-creator

Create or improve Zhin Agent skills (SKILL.md). Use when asked to add a skill, write SKILL.md, document a repeatable agent workflow, or refine skill frontmatter/keywords. Triggers: 创建技能, 写 SKILL, skill-creator, 加 skill.

zhinjs/zhin · 61 tokens

skill-based-architecture

This skill should be used when the user asks to "organize the project rules", "clean up scattered documentation", "把规则迁移到 skills 目录", "优化 skill 路由", "提高 description 命中率", or "减少薄壳重复维护". Activate when a SKILL.md is too large, rules are duplicated across agent entry files, task routing or triggerexamples miss natural…

WoJiSama/skill-based-architecture · 103 tokens

llm-council

Convene a cross-vendor LLM council — the main session acts as Chairman and spawns several subagents, each pinned to a DIFFERENT model (Anthropic / OpenAI / DeepSeek / Zhipu / Qwen / etc. via kiro-cli). Three modes — synthesis (independent answers merged into one), vote (structured ballots + majority tally), and…

kirodotdev/KiroCrew · 209 tokens

rolecraft

Install AI agent skills as roles & behaviors from any source — local folder, GitHub, GitLab, SSH git URL. Zero-dependency CLI with 87 agent targets (27 verified).

rolecraft-sh/rolecraft · 41 tokens

subagent-orchestrator

Orchestrate subagent workflows for complex tasks that benefit from decomposition, role-based delegation, and parallel execution. Use when Codex should assemble a temporary team of subagents, choose roles from a reusable role library, create a controlled fallback role when no preset role fits, coordinate read-heavy…

flc1125/skills · 87 tokens