grill-skill

grill-skill is a skill for Claude Code from edonadei/caliper. It costs 57 tokens per session (745 once invoked), scanned A, original, MIT.

A guided method for creating or improving a coding-agent skill through evaluation. It interviews the user about test tasks, then runs, measures, and improves the skill until it is ready.

In plain words
What is it for?
Use it to design or refine a skill’s evaluation, write evaluation specifications, run the test-and-improve loop, and verify expected agent behavior.
Why use it?
It turns vague skill quality into repeatable checks, including normal use and tricky valid inputs, so weaknesses can be found before release.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to design or refine a skill’s evaluation, write evaluation specifications…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/edonadei/caliper/grill-skill
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.

Any agent
npx skills add edonadei/caliper --skill grill-skill
Clone the repo
git clone --depth 1 https://github.com/edonadei/caliper

Made for: Claude Code.

Wrote 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.

agentmods badge for grill-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/edonadei/caliper/grill-skill.svg)](https://agentmods.dev/skills/edonadei/caliper/grill-skill)
Your own site
<a href="https://agentmods.dev/skills/edonadei/caliper/grill-skill"><img src="https://agentmods.dev/badge/skills/edonadei/caliper/grill-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00057 $0.00745
Opus 5 $0.00028 $0.00373
Sonnet 5 $0.00011 $0.00149
Haiku 4.5 $0.00006 $0.00075

Measured 7d ago against content hash ccbeb4385055, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

grill-skill 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 7d 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/grill-skill/SKILL.md · 56 lines

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.

Grill Skill

Interview the user to design a skill's eval, then loop run → measure → improve until it ships. Requires caliper (pipx install caliper-eval if missing). Commands, spec skeleton, and expect/assert guidance: REFERENCE.md.

Entry point

/grill-skill [path] — optional path to a SKILL.md.

  • Path given — use it.
  • No path — look for SKILL.md in the cwd; if found, confirm before proceeding, else ask where it is.

Phase 1 — Understand

Read the SKILL.md. Summarize what it does, when it triggers, and what a successful run looks like. Ask the user to confirm your reading. Wait for confirmation before continuing.

Phase 2 — Detect eval mode

Look for *.eval.yaml beside the SKILL.md (try <dir-name>.eval.yaml first).

  • None → New eval. Found → Gap-fill.

Interview one question at a time and wait for each answer. Never invent the user's answers or write the spec before interviewing.

New eval — three tasks

Elicit three tasks, one question at a time:

  1. Happy path — the most common successful use. What did the agent do, and what would confirm it worked?
  2. Edge case — a tricky-but-valid input that might trip the raw agent.
  3. Adversarial — what the skill should refuse or avoid.

Turn each answer into a task: a realistic prompt, an observable expect, and an assert when the outcome is checkable (see REFERENCE.md). Show the proposed YAML and confirm before writing.

Write the spec beside SKILL.md, named <dir-name>.eval.yaml, with skill.path: ./SKILL.md and claude-code as the default backend for both skill and judge unless the SKILL.md targets another.

Gap-fill

Read the existing spec and report its tasks. Ask what behaviors are missing or under-tested before proposing or writing anything — even if the user only asked you to inspect it, report first, then ask. Sharpen each gap into a task, show it, and confirm before writing it in.

Phase 3 — First run

Read the full file on GitHub · 56 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. 7d ago First seen · 56 lines · 57 tokens per session scan A ccbeb4385055

Subscribe to this mod's changes

grill-skill is a skill published in the GitHub repository edonadei/caliper (50 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 745 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

skillshare-implement-feature

Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…

runkids/skillshare · 114 tokens

agent-eval

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…

ericrisco/rsc-harness · 79 tokens

skillshare-cli-e2e-test

Run isolated E2E tests in devcontainer from aidocs/tests runbooks. Use this skill whenever the user asks to: run an E2E test, execute a test runbook, validate a feature end-to-end, create a new runbook, or test CLI behavior in isolation. If you need to run a multi-step CLI validation sequence (init → install → sync →…

runkids/skillshare · 127 tokens

hz-xr-simulator-setup

Sets up the Meta XR Simulator for testing Meta Quest and Horizon OS apps without a physical device. Use when configuring device-free testing for Unity or Unreal projects.

meta-quest/agentic-tools · 39 tokens

cf-tdd

Use when writing new production code, adding features, implementing, or refactoring — e.g. "implement this", "build this feature", "create a function", "add a new endpoint", "write the implementation", "refactor this", "write a test", "add tests", "create a component", "implement the API", "add a route". Also…

dinhanhthi/coding-friend · 136 tokens

cf-verification

Verify before claiming work is complete.

dinhanhthi/coding-friend · 10 tokens