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/blendsdk/claude-codeops/grill_menpx skills add blendsdk/claude-codeops --skill grill_megit clone --depth 1 https://github.com/blendsdk/claude-codeopsWhat 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 | $0.00142 | $0.03884 |
| Opus 5 | $0.00071 | $0.01942 |
| Sonnet 5 | $0.00028 | $0.00777 |
| Haiku 4.5 | $0.00014 | $0.00388 |
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 2d 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Disambiguation Protocol (grill_me)
When the user types grill_me (with or without additional context), enter
relentless interview mode — a structured, branch-by-branch interrogation
designed to eliminate every ambiguity before any plan, requirement, or
implementation work begins.
CodeOps Skills Version: 3.20.0
Core Directive
Interview the user relentlessly about every aspect of the topic until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.
You are NOT a polite assistant trying to move fast. You are a senior architect conducting a design review. Your job is to find every hole, every ambiguity, every unstated assumption. Be thorough. Be persistent. Do not accept vague answers — ask for specifics. Do not assume you understand — verify explicitly.
Before you begin, read the project's CLAUDE.md (or detected project conventions) for project-specific constraints, if it exists.
When to Use
| Usage Pattern | What the User Types | What Happens |
|---|---|---|
| Standalone deep-dive | grill_me + topic description |
Full interrogation on the topic. Output: shared understanding summary. |
| Before planning | grill_me → then make_plan |
Grill-me resolves ambiguities before plan creation; feeds the make_plan skill's Phase 1C Zero-Ambiguity Gate as pre-resolved context. |
| Before requirements | grill_me → then make_requirements |
Grill-me deeply explores the topic before structured RD authoring; feeds the make_requirements skill's Phase 2B gate. |
| Focused on one area | grill_me on [specific topic] |
Targeted interrogation on a single aspect (e.g., "grill_me on the auth flow"). |
The Protocol
Step 0: Classify the domains
Before mapping the tree, classify the system from repository evidence and the user's stated topic using ../../references/domains/selection.md. Present the selection with the evidence behind each domain and let the user amend it.
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.
- 2d ago First seen · 365 lines · 142 tokens per session scan A ca5a1635f190
grill_me is a skill published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 3,884 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…