Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/notque/vexjoy-agentnpx agentmods add skills/notque/vexjoy-agent/grill-jevWrote 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/notque/vexjoy-agent/grill-jev)<a href="https://agentmods.dev/skills/notque/vexjoy-agent/grill-jev"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/grill-jev/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/notque/vexjoy-agent/grill-jev"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/grill-jev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00048 | $0.03697 |
| Opus 5.5 | $0.00019 | $0.01479 |
| Sonnet 5.5 | $0.00010 | $0.00739 |
| Haiku 4.5 | $0.00005 | $0.00370 |
Grade A, and why
grill-jev scanned grade A with 1 finding 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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill-Jev
Generate a context-specific Jev interrogation battery against a plan, spec, design, code artifact, or any topic. Questions are generated from the artifact itself — not from a static list — so they target the actual risks and gaps in what you provide.
When to invoke
- User says "grill this", "validate my plan", "find holes in my spec", "sanity check", "stress test this", "50 questions", "interrogate", "grill-jev"
- Automatically after any planning output. When a plan, spec, or design is produced — before execution begins — pass it through grill-jev. Any structured output with phases, steps, or checklist items qualifies.
- When the user says "does this look right", "approve this", "is this ready", "review my plan"
How it works
- Read the artifact — the plan, spec, design, or code being interrogated
- Generate questions — the LLM executing this skill produces up to 50 context-specific Jev questions tailored to the artifact. It writes the JSON battery to a temporary file; no secondary model call or API key is used. Questions use all structured shapes:
- Noul with
{true: {what, examples}, false: {what, examples}}criteria - Choice with
{what, not_for, examples}per option - Score with
{summary, signals}per level - Noul with array
compareinstructions when two state paths need comparison
- Noul with
- Send to Jev — evaluate the questions against the artifact as state. Use Vercel AI Gateway. Too much context is the most common failure: the artifact is resent with every batch, so split the battery by estimated tokens (
jev_limits.request_tokens), not by question count, keeping each request under the size target inskills/shared-patterns/jev-production-lessons.md. When the artifact alone passes the target, send the sections each question needs instead of the whole artifact.scripts/grill-jev.pydoes the splitting: it packs batches by tokens, and when a batch fails it halves and retries down to single questions, so one oversized or malformed question costs only its own answer. A question that still fails is listed as UNANSWERED (unknown, never a pass) and the run exits 2. If a tiny probe also fails, Jev is down and the run stops. The script rejects a malformed battery before sending (for example, Score levels must be a list). - Report findings — high-signal answers with suggested actions
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.
- today Changed · +17 lines 88f4c4adf2dd
- 20d ago Changed a264121beea3
- 23d ago Changed · +11 lines c065a8ff8741
- 24d ago First seen · 259 lines · 48 tokens per session scan A bb2b3ecb0d59
grill-jev is a skill published in the GitHub repository notque/vexjoy-agent (442 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 3,697 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
godot-code-review
Use when reviewing GDScript or C# Godot code — checklist of best practices, common anti-patterns, and Godot-specific pitfalls. Triggers on "review this script", "check my code", "any issues with this", "what's wrong with this code", including a short pasted snippet.
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
squid-architecture-review
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.
squid-implement-night
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.
pr-review
AUTHOR SKILL (internal to microsoft/aspire-skills). Reviews pull requests into this repo for problems only — bugs, regressions, missing eval coverage, frontmatter or routing damage, plugin-manifest drift, hook safety, and other concrete issues. Drives a six-step workflow: identify the PR, ensure the branch is…
clean-code
Code quality: meaningful names, SRP, DRY, small functions, guard clauses, refactoring. Triggers: clean code, naming, code smell, SRP, DRY, long function, god class, dead code.