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 hollandkevint/thinkhaven --skill grill-with-docsgit clone --depth 1 https://github.com/hollandkevint/thinkhavenWrote 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/hollandkevint/thinkhaven/grill-with-docs)<a href="https://agentmods.dev/skills/hollandkevint/thinkhaven/grill-with-docs"><img src="https://agentmods.dev/badge/skills/hollandkevint/thinkhaven/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/hollandkevint/thinkhaven/grill-with-docs"><img src="https://agentmods.dev/badge/skills/hollandkevint/thinkhaven/grill-with-docs.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 | $0.00138 | $0.01340 |
| Opus 5 | $0.00069 | $0.00670 |
| Sonnet 5 | $0.00028 | $0.00268 |
| Haiku 4.5 | $0.00014 | $0.00134 |
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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill With Docs
Work a build idea through with the agent until it is sharp enough to implement, grounded in this repository's real code and documented decisions, and leave behind a durable record.
This is the collaborative, file-grounded member of the grill family. Unlike a paste-driven grill, you have the filesystem: read the code, check the docs, validate claims against what is actually there. Use it before writing code on anything non-trivial (a schema change, a new API surface, a board/persona behavior, a credit/auth path).
For: shaping a feature or decision against the real codebase, with shared understanding and a captured record as the output.
Not for: pure idea generation (use ce-brainstorm), writing an implementation plan (ce-plan), or post-hoc documentation of work already shipped (/compound).
The loop
- Restate the decision in one sentence. Confirm you and the user mean the same thing before grilling.
- Ground before you ask. When a question can be answered from the repo, answer it from the repo. Do not speculate or ask the user to recite what the code already says. Read first:
CLAUDE.md(project rules, pitfalls, model/cost posture, conventions)docs/solutions/(prior decisions and learnings;grep -r "<term>" docs/solutions/)- the actual source for the area in question (
lib/,app/,supabase/migrations/)
- Walk the decision tree one branch at a time. Ask exactly ONE question, then wait. For each question, give your recommended answer first so the user can accept it, correct it, or expose the hard part. Resolve dependencies before moving on.
- Cross-check claims against code. When the user states behavior, verify it. Surface contradictions plainly: "You said partial cancellation is supported, but
session-primitives.ts:deleteSessiondrops the whole row. Which is right?" Code is ground truth; a user's mental model is a hypothesis. - Sharpen the language. Challenge fuzzy or overloaded terms immediately. Propose one canonical term when several describe the same thing. Distinguish domain terms from code/module names. Keep this in-conversation. Do not spin up a separate glossary file (this repo does not keep one).
- Capture as you resolve (see below). Do not batch to the end.
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.
- 5d ago First seen · 68 lines · 138 tokens per session scan A 934e9587efe1
grill-with-docs is a skill published in the GitHub repository hollandkevint/thinkhaven (5 stars, last pushed 10d ago), licensed Apache-2.0. It adds 138 tokens to every session and 1,340 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 2026-09-03.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…