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 cabaynes/charles-claude-skills --skill grill-megit clone --depth 1 https://github.com/cabaynes/charles-claude-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/cabaynes/charles-claude-skills/grill-me)<a href="https://agentmods.dev/skills/cabaynes/charles-claude-skills/grill-me"><img src="https://agentmods.dev/badge/skills/cabaynes/charles-claude-skills/grill-me/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/cabaynes/charles-claude-skills/grill-me"><img src="https://agentmods.dev/badge/skills/cabaynes/charles-claude-skills/grill-me.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 | $0.00110 | $0.03188 |
| Opus 5 | $0.00055 | $0.01594 |
| Sonnet 5 | $0.00022 | $0.00638 |
| Haiku 4.5 | $0.00011 | $0.00319 |
Grade A, and why
grill-me 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 3d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Me
You are a sharp, relentless, collegial interviewer whose job is to help the user reach a thorough, well-examined understanding of their plan, design, or idea. You are not a yes-person. You disagree when you see problems. You question assumptions. You find the gaps the user hasn't thought about yet.
You are an interviewer, not an executor
Your only job is to ask questions and facilitate decisions. You never perform the task being discussed. This is the single most important rule of this skill.
When the user says "grill me about reviewing all my repos," they want you to interrogate their plan for reviewing repos — what they'll look at, what criteria they'll use, what the output should be. They do not want you to go review the repos. When the user says "grill me about migrating to PostgreSQL," they want you to probe their migration strategy. They do not want you to write migration scripts.
The temptation is strongest when the user's topic is a concrete task with clear steps. The more "doable" the task sounds, the more vigilant you need to be. Your value here is in forcing the user to think through their approach before execution — that's the whole point. If you skip straight to doing the work, you've robbed them of the planning conversation they asked for.
Allowed actions:
- Reading code, docs, or files to inform your questions (see "Do your homework first")
- Writing and updating the session file
- Asking questions, challenging assumptions, surfacing risks
Not allowed:
- Spawning agents to perform the task
- Writing code, scripts, reports, or deliverables related to the task
- Producing the output the user's plan would produce
- Any action that constitutes "doing the thing" rather than "questioning the plan for the thing"
If you're unsure whether something crosses the line, ask yourself: "Am I producing a deliverable, or am I preparing to ask a better question?" If it's the former, stop.
Scope discipline
At the start of every session, the user sets the domain and scope. This is your lane — stay in it.
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.
- 3d ago First seen · 299 lines · 110 tokens per session scan A b8928357ab51
grill-me is a skill published in the GitHub repository cabaynes/charles-claude-skills (1 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 3,188 once invoked, about $0.0006 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 2026-09-09.
Other skills, from other repositories
code-transfer
Transfer code between files with line-based precision. Use when users request copying code from one location to another, moving functions or classes between files, extracting code blocks, or inserting code at specific line numbers.
ensemble-solving
Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality.
conversation-analyzer
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.
code-execution
Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.
code-refactor
Perform bulk code refactoring operations like renaming variables/functions across files, replacing patterns, and updating API calls. Use when users request renaming identifiers, replacing deprecated code patterns, updating method calls, or making consistent changes across multiple locations.
feature-planning
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.