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 skills add edonadei/caliper --skill grill-skillgit clone --depth 1 https://github.com/edonadei/caliperWrote 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/skills/edonadei/caliper/grill-skill)<a href="https://agentmods.dev/skills/edonadei/caliper/grill-skill"><img src="https://agentmods.dev/badge/skills/edonadei/caliper/grill-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/edonadei/caliper/grill-skill"><img src="https://agentmods.dev/badge/skills/edonadei/caliper/grill-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01957 |
| Opus 5.5 | $0.00023 | $0.00783 |
| Sonnet 5.5 | $0.00012 | $0.00391 |
| Haiku 4.5 | $0.00006 | $0.00196 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 95 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 → diagnose → improve until it ships. Requires caliper (pipx install caliper-eval if missing). Commands, spec skeleton, and task-writing rules: REFERENCE.md.
An eval answers four questions, and the interview covers each:
- Fires: does the agent reach for the skill when it should, and only then? Tested with
activates:and trigger probes. Fixed in thedescription. - Works: once it fires, does it do the job? Tested with
expect:/assert:. Fixed in the body. - Earns: does it beat the agent without it? Tested against the control: the declared neighbourhood with this skill removed. A task the control passes too is fixed in the task.
- Holds: does it stay good across edits? Tested by comparing each new full run against the previous one.
Entry point
/grill-skill [path]: optional path to a SKILL.md.
- Path given: use it.
- No path: look for
SKILL.mdin 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. Build every task from the user's answers, and write the spec only after the interview.
New eval
Elicit, one question at a time:
- Happy path: the most common successful use. What did the agent do, and what would confirm it worked?
- Edge case: a tricky-but-valid input that might trip the bare agent.
- Adversarial: what the skill should refuse or avoid.
- Neighbours: which other skills could an agent confuse with this one? For each one the user can point to (a path or a git repo), declare it in
skills:and add a neighbour probe: a prompt that belongs to the neighbour, withactivates: [<neighbour>].
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.
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.
- 12d ago Changed 1b6c839e49a2
- 13d ago Changed e37a17486f4a
- 26d ago Changed · +33 lines · +1 tokens per session 20b4c792666f
- 27d ago Changed · +6 lines 02d0ef83e633
- 1mo ago First seen · 56 lines · 57 tokens per session scan A ccbeb4385055
grill-skill is a skill published in the GitHub repository edonadei/caliper (217 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 1,957 once invoked, about $0.0002 per session on Opus 5.5. 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 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…
skillshare-windows-utm
Verify skillshare on a real Windows guest running in local UTM: build a pinned commit in the devcontainer, push it into the VM, and either run the Windows E2E runbook with full and basic-user tokens or hand the maintainer a one-line hands-on setup. Use this whenever a change touches Windows links, junctions, file…
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…
hz-unity-device-readiness
Audits a Unity project for Meta VR Glasses readiness across input and field of view — finds controller-dependent interactions such as OVRInput usage, recommends hand-tracking and ISDK controller-to-hands migrations, produces a prioritized migration plan, and detects head-locked UI that a narrower FoV would clip.
hz-xr-simulator-control
Routes Meta VR and Horizon OS simulator work to the right metavr command group, and drives a running Meta XR Simulator via metavr xrsim — runtime, device, input, compositor layers and MP4 recording. Use when a goal concerns a simulated headset rather than a physical one, when choosing between xrsim, ssim, capture and…
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 →…