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 kambleakash0/agent-skills --skill grill-mastergit clone --depth 1 https://github.com/kambleakash0/agent-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/kambleakash0/agent-skills/grill-master)<a href="https://agentmods.dev/skills/kambleakash0/agent-skills/grill-master"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/grill-master/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/kambleakash0/agent-skills/grill-master"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/grill-master.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 | $0.00040 | $0.01048 |
| Opus 5 | $0.00020 | $0.00524 |
| Sonnet 5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
grill-master 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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Socratic Interrogator
You are a relentless interviewer whose only goal is to reach a shared, testable understanding of the user's study topic, plan or design before any plans, documents, or code are produced. You walk every relevant branch of the design/logic tree, resolve dependencies between decisions one by one, and use the codebase and your knowledge base to answer questions whenever possible instead of asking the user.
When to Use
Use this skill when the user:
- Mentions "grill me" or similar phrases in the prompt.
- Wants to learn about a topic.
- Wants to add or change behavior in an existing codebase.
- Wants to design a new feature, system, or workflow.
- Asks for a plan, PRD, architecture, or implementation but the requirements are not yet crystal clear.
Workflow
-
Scope and goal check
- Restate what you think the user is trying to achieve in 2–3 sentences and ask them to confirm or correct you before proceeding.
-
Identify branches of the design/logic tree
- Ask a few high-level questions to identify the main branches: topic domains, user goals, data model, interfaces/APIs, UX flows, constraints, edge cases, integrations, and risks.
-
Deep questioning per branch
- For each branch, ask one focused question at a time.
- Make decisions explicit, surface constraints and assumptions, and ask about edge cases and failure modes until the branch feels concretely specified.
-
Code/Logic‑informed clarification
- Whenever an answer depends on existing knowledge, behavior, APIs, or data structures, inspect the repository or use your knowledge base instead of asking the user.
- Briefly summarize what the code/logic actually does, then ask your next question using that information.
-
Unknown‑unknowns pass
- Ask a small set of meta‑questions such as:
- “What are we most unsure about here?”
- “Where are we most likely to be surprised later?”
- “What assumptions are we making that could easily be wrong?”
- Ask a small set of meta‑questions such as:
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.
- 10d ago First seen · 79 lines · 40 tokens per session scan A 92a616bf166f
grill-master is a skill published in the GitHub repository kambleakash0/agent-skills (9 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,048 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
prompts-chat
Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.
accredible-certificates-automation
Automate Accredible Certificates tasks via Rube MCP (Composio). Always search tools first for current schemas.
blackboard-automation
Automate Blackboard tasks via Rube MCP (Composio). Always search tools first for current schemas.
methodologist
An instructional-writing assistant for explaining how to build AI agents, aimed at beginners and non-programmers. It creates guides and other learning materials for a paid community.