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 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/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/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="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 | $0.00050 | $0.00596 |
| Opus 5.5 | $0.00020 | $0.00238 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 5mo ago), licensed MIT. It adds 50 tokens to every session and 596 once invoked, about $0.0002 per session on Opus 5.5. 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
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
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.