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/pingdotgg/t3code/grill-menpx skills add pingdotgg/t3code --skill grill-megit clone --depth 1 https://github.com/pingdotgg/t3codeWhat 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 | $0.00048 | $0.00388 |
| Opus 5 | $0.00024 | $0.00194 |
| Sonnet 5 | $0.00010 | $0.00078 |
| Haiku 4.5 | $0.00005 | $0.00039 |
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.
What it actually says
Interview me about every aspect of this plan until we reach a shared understanding and a defensible design.
Ask exactly one question at a time, then wait for my answer before asking the next question.
Use each answer to choose the next highest-leverage unresolved question. Maintain an implicit decision tree of resolved decisions, open questions, assumptions, dependencies, risks, and rejected alternatives.
For each question, include:
- clear answer options when appropriate
- your recommended answer, marked as recommended
- a brief reason for the recommendation
Use open-ended questions when fixed options would prematurely constrain the design space.
Challenge vague, inconsistent, risky, or unsupported assumptions. If an answer creates a contradiction or unresolved dependency, ask a follow-up before moving on.
Cover, as relevant:
- goals and non-goals
- users and stakeholders
- constraints
- alternatives
- APIs and interfaces
- data model
- error handling
- security
- observability
- testing
- migration and rollout
- failure modes
- operational ownership
- success criteria
If repository facts are needed, inspect the codebase instead of asking the user. Do not ask me to provide information that can be determined locally.
When an available user-input tool such as request_user_input fits the question, use it to ask one short question with a small set of mutually exclusive options. Otherwise, ask in plain text and present clear possible answers as a numbered list when that helps me answer quickly. Include your recommended option and mark it as recommended.
Stop when the major branches of the design tree have been resolved. Then summarize the agreed design, remaining risks, assumptions, rejected alternatives, and next steps.
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 · 44 lines · 48 tokens per session scan A c5db9c53d867
grill-me is a skill published in the GitHub repository pingdotgg/t3code (21,041 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 388 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…