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 r13v/pi-feature-dev --skill grillgit clone --depth 1 https://github.com/r13v/pi-feature-devWrote 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/r13v/pi-feature-dev/grill)<a href="https://agentmods.dev/skills/r13v/pi-feature-dev/grill"><img src="https://agentmods.dev/badge/skills/r13v/pi-feature-dev/grill/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/r13v/pi-feature-dev/grill"><img src="https://agentmods.dev/badge/skills/r13v/pi-feature-dev/grill.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 | $0.00050 | $0.02454 |
| Opus 5.5 | $0.00020 | $0.00982 |
| Sonnet 5.5 | $0.00010 | $0.00491 |
| Haiku 4.5 | $0.00005 | $0.00245 |
Grade A, and why
grill 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 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.
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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill
Interview the user until both sides share an explicit, evidence-backed understanding. Model the topic as a decision tree, research discoverable facts, challenge the domain language, and record settled terminology and durable decisions as they crystallize.
Keep the interview separate from implementation. Capturing agreed terminology and accepted ADRs is part of the session. An interview-only request ends with the confirmed result. If the user already requested planning or implementation afterward, continue that work after the interview resolves its prerequisites; do not require them to repeat the request.
Core distinctions
- Treat a fact as something discoverable from the environment, artifacts, documentation, or code. Find it yourself.
- Treat a decision as a choice among viable alternatives. Put it to the user with a recommendation.
- Treat a prerequisite as a fact or decision that must settle before a downstream question can be answered without guessing.
- Treat the frontier as every unresolved decision whose prerequisites are settled now.
Never turn a discoverable fact into homework for the user. Never silently turn an unresolved decision into an assumption. When the user delegates a decision, state the chosen option and trade-off and treat that delegation as sufficient.
Resolve bundled resources
Before invoking a read for any relative reference in this skill, resolve it
against the directory containing the selected grill/SKILL.md. Use that
resolved path for the read. Never use the global skills directory, the current
working directory, or the repository root as the base.
Workflow
1. Establish the subject
Restate the outcome being explored, the requested deliverable, and any explicit constraints. Mark interpretations as provisional until the user confirms them.
Build a mental decision tree rooted in that outcome. Add only branches that can materially change the result, such as:
- scope and non-goals
- actors, responsibilities, and boundaries
- domain terms and invariants
- lifecycle, states, and failure behavior
- data ownership and integration points
- usability, security, performance, or operational constraints
- trade-offs, validation, rollout, and reversibility
What ships with it
3 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 · +30 lines 74da917fe278
- 9d ago Changed · +78 lines 0f460c0cd75c
- 10d ago Changed c6e328725dca
- 18d ago Changed · +2 lines · +18 tokens per session d91644eb443d
- 1mo ago Changed · +15 lines 9ac892f56b8c
- 1mo ago Changed · +8 lines 3224dede76ed
- 1mo ago Changed · -46 tokens per session 2c6cef504a2a
- 2mo ago First seen · 127 lines · 78 tokens per session scan A 6f3151e2f3b2
grill is a skill published in the GitHub repository r13v/pi-feature-dev (3 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 2,454 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…