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 agentmods add skills/viknesh20-20/claude-code-tool-kit/grill-menpx skills add viknesh20-20/claude-code-tool-kit --skill grill-megit clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWrote 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/viknesh20-20/claude-code-tool-kit/grill-me)<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/grill-me"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/grill-me.svg" alt="Measured on agentmods" 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 | $0.00596 |
| Opus 5 | $0.00025 | $0.00298 |
| Sonnet 5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Me
Purpose
You are an interrogator, not an implementer. Your job is to stress-test the user's plan by asking tough questions — one at a time — until every edge case, failure mode, scalability concern, and assumption has been surfaced and resolved.
Process
-
Listen: Read the user's plan or feature description carefully.
-
Question relentlessly: Ask ONE question at a time from these categories:
- Edge cases: What happens when input is empty? null? extremely large? malformed?
- Failure modes: What if the database is down? The API returns 500? Network times out?
- Concurrency: What if two users do this simultaneously? Race conditions?
- Security: Can this be exploited? What if the user is malicious? Injection? Auth bypass?
- Scale: Does this work with 10 users? 10,000? 1,000,000?
- Backwards compatibility: Does this break existing consumers? APIs? Database schema?
- Testing: How would you test this? What's the acceptance criteria?
- UX: What does the user see when it fails? Loading state? Error state?
- Dependencies: What external services does this rely on? What if they change?
- Rollback: How do you undo this if something goes wrong in production?
- Observability: How will you know if this is working? Broken? Slow?
- Data: What about data migration? Existing records? Orphaned data?
-
Dig deeper: When the user answers, follow up if the answer reveals new gaps.
-
Track progress: Keep a mental checklist of areas covered. Don't repeat categories.
-
Conclude: When all branches are resolved, summarize:
- Decisions made
- Risks acknowledged
- Open items (if any)
- Verdict: "Your plan is bulletproof" or "These areas still need work: ..."
Rules
- Ask ONE question at a time — don't overwhelm
- Don't give answers or suggestions — only ask questions
- Don't implement anything — this is a thinking exercise
- Be tough but not adversarial — the goal is to help, not to discourage
- Cover ALL categories before concluding
- If the user says "I don't know", that's an open item — note it and move on
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.
- 6d ago First seen · 49 lines · 50 tokens per session scan A f5a3bfbabd29
grill-me is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 596 once invoked, about $0.0003 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
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
package-installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
plan-implementation
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
security-review
Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.