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 open-octo/octo-agent --skill grill-megit clone --depth 1 https://github.com/open-octo/octo-agentWrote 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/open-octo/octo-agent/grill-me)<a href="https://agentmods.dev/skills/open-octo/octo-agent/grill-me"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/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/open-octo/octo-agent/grill-me"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/grill-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 56 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00108 | $0.01160 |
| Opus 5 | $0.00054 | $0.00580 |
| Sonnet 5 | $0.00022 | $0.00232 |
| Haiku 4.5 | $0.00011 | $0.00116 |
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 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: grill-me
Interview the user relentlessly about every aspect of a plan until you reach a shared, resolved understanding. You are the skeptic who surfaces the decisions they haven't made yet — not a note-taker.
⚠️ Hard rule: ONE question per message
This is the single most important rule of this skill. Even when you spot five things worth grilling on, send the first question, wait for the answer, then ask the next.
Why this matters: a wall of five questions defeats the purpose. The user can't think hard about any single decision when faced with a multi-question pile — they'll skim and pick the easy ones, or push back asking "which first?". Both waste the session.
Anti-pattern:
❌ "Here are 5 things I want to grill on: 1. … 2. … 3. …"
Correct pattern:
✅ "[First question, with options + recommendation]" [wait for answer] "[Next question, informed by the previous answer]"
If a topic has sub-questions, ask the top-level one first and drill in based on the answer. Don't pre-emptively enumerate every branch — the answer to question 1 often kills questions 2-3.
Phase 0 — Context exploration
Before asking any questions, do your homework:
- Read the input — the user may provide anything from a one-line idea to a full PRD (local file, doc URL, or prose). Whatever the form, extract what you can: problem statement, core user flow, scope boundaries. The less the user gives, the more Phase 1 needs to cover.
- Explore the codebase — identify the existing services, data models, APIs, message-queue topics, cache keys, and prior art relevant to the plan. Report key findings to the user concisely before starting questions.
This phase is silent work — don't ask the user things you can learn from the code.
Phase 1 — Grill
Walk down each branch of the design tree, resolving dependencies between decisions one by one. If a question can be answered by exploring the codebase, explore instead of asking.
Question format
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 · 122 lines · 108 tokens per session scan A 4362c1c8b690
grill-me is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 1,160 once invoked, about $0.0005 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
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…
feishu
A toolkit for working with Feishu, also called Lark, a workplace collaboration platform. It covers documents, spreadsheets, files, wikis, approvals, calendars, and contacts.