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 arozumenko/sdlc-skills --skill grill-decisiongit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/grill-decision)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/grill-decision"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/grill-decision/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/arozumenko/sdlc-skills/grill-decision"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/grill-decision.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 | $0.00176 | $0.03340 |
| Opus 5 | $0.00088 | $0.01670 |
| Sonnet 5 | $0.00035 | $0.00668 |
| Haiku 4.5 | $0.00018 | $0.00334 |
Grade A, and why
grill-decision 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grill-decision
Interview the user one question at a time until you reach a shared, sharp understanding. For each question, propose your recommended answer with a short justification — don't ask open-ended "what do you think?" questions when you can take a position the user can react to.
Walk down the decision tree branch by branch. Resolve dependencies between decisions one at a time. Wait for feedback on each question before moving to the next.
Whenever a question can be answered by reading what already exists — .agents/profile.md, the
project's docs/, docs/discovery/decisions.md, the Hypotheses, prior evidence — read
instead of asking. The user has already invested in those documents; don't make them retell
what's written down.
Capture outcomes inline as they crystallize — never batch to the end of the session. A term
that just got sharpened is corrected now, in the artifact that used it; a decision that just got
made becomes a DEC entry in docs/discovery/decisions.md now; a Hypothesis that just got
sharpened gets edited now. Inline writes survive an interrupted session; a wall of edits at the
end does not. Note progress via the memory skill's Log op after each inline capture, before
the next question.
What this skill reads (config, by name — never restated here)
Read these at the start of a session; they replace every hardcoded domain fact:
.agents/profile.md— the project's guardrails and constraints (whatever form they take for this product — scope lines, non-negotiable rules, compliance requirements). These are the challenge lenses (below): every recommendation and every Hypothesis passes through all of them. A guardrail marked non-negotiable or a hard boundary is an emergency brake — a recommendation that trips it is not viable as written, surface it, don't paper over it..agents/profile.mdand the project'sdocs/— the product one-liner, phase framing, the surfaces this product owns, and any decision convention already in use for flagging work that depends on an unresolved call (generalize on the pattern// PENDING_DECISION_DEC-NNN: assuming [option] because [reason]if the project has none of its own).docs/discovery/decisions.md— the append-only DEC log (id | date | decision | rationale | supersedes). This file, not this skill, is the canonical home of decisions.
What ships with it
1 file 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 First seen · 219 lines · 176 tokens per session scan A fcf8630a3025
grill-decision is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed today), licensed MIT. It adds 176 tokens to every session and 3,340 once invoked, about $0.0009 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…