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 haowjy/creative-writing-skills --skill grill-with-docsgit clone --depth 1 https://github.com/haowjy/creative-writing-skillsWrote 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/haowjy/creative-writing-skills/grill-with-docs)<a href="https://agentmods.dev/skills/haowjy/creative-writing-skills/grill-with-docs"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/grill-with-docs/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/haowjy/creative-writing-skills/grill-with-docs"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/grill-with-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00830 |
| Opus 5 | $0.00012 | $0.00415 |
| Sonnet 5 | $0.00005 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
grill-with-docs 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill With Docs
Load /intent-modeling if it isn't already loaded.
Interview the author relentlessly about every aspect of their plan until you reach a shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one by one.
Keep each turn to the next unresolved branch or a small cluster of related questions the author can answer in one reply, then wait. Provide your recommended answer for each question.
Starting the Session
Read the plan or proposed direction the author provides. Identify:
- Decision branches — choices that gate other choices
- Dependency order — which decisions must resolve first
- Terms needing precision — vague, overloaded, or undefined vocabulary
- Assumptions — things treated as given that may not be
Start with the highest-leverage unresolved dependency — the earliest branch point that unblocks the most downstream decisions.
Challenging Terminology
Check every significant term against the project's existing vocabulary where it exists:
- Vocabulary pages in the kb —
kb/vocab.mdfor project-wide terms,kb/<domain>/vocab.mdfor domain-specific ones. - Project conventions in
CLAUDE.md— established names and labels. - Active work notes in
work/— terms already defined for the current effort. - Prior decisions — terms established by earlier choices.
When the author's language conflicts with documented terms, call it out immediately. Name the conflict: "You said X, but the kb defines Y for this concept — which should we use?"
Sharpen vague or overloaded terms into canonical terms. Use concrete
scenarios and edge cases to force precise boundaries — "Does 'sync' here mean
the timeline beat, the character's realization, or something new?" See
/shared-dao for the vocabulary discipline.
Gathering Evidence
When answering requires cross-referencing project materials beyond what is already in context, read the specific files directly, or spawn a focused subagent to gather evidence so your own context stays on the grilling conversation. Scope each lookup to one question and target specific files or directories — chapters, kb entries, outlines, prior decisions.
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 · 102 lines · 23 tokens per session scan A 1d7b1487bc08
grill-with-docs is a skill published in the GitHub repository haowjy/creative-writing-skills (454 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 830 once invoked, about $0.0001 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…