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/miaodx/intuitive-flow/grill-with-docs-batchnpx skills add MiaoDX/intuitive-flow --skill grill-with-docs-batchgit clone --depth 1 https://github.com/MiaoDX/intuitive-flowWrote 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/miaodx/intuitive-flow/grill-with-docs-batch)<a href="https://agentmods.dev/skills/miaodx/intuitive-flow/grill-with-docs-batch"><img src="https://agentmods.dev/badge/skills/miaodx/intuitive-flow/grill-with-docs-batch.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.02279 |
| Opus 5 | $0.00036 | $0.01140 |
| Sonnet 5 | $0.00014 | $0.00456 |
| Haiku 4.5 | $0.00007 | $0.00228 |
Grade A, and why
grill-with-docs-batch 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill With Docs Batch
Challenge a plan against the repository's domain model and documentation like
grill-with-docs, but move in small coherent batches instead of one question at
a time.
First Decide Whether To Stop
Before asking any batch, run a saturation audit:
- Read the target plan/ADR/spec and the domain glossary or context file it depends on.
- Check recent git history for the same target docs when available, but use it only as supporting evidence. Commit count is not a stop condition by itself; it helps find decisions that were already made and areas that may be getting re-litigated.
- Separate durable decision questions from implementation defaults. Do not ask the user to discuss things the implementation can decide locally without changing public contracts, private-data boundaries, safety policy, cost/model infrastructure, or irreversible file moves.
- If an ADR is accepted, a plan names what changes, what is out of scope, the important boundaries, the acceptance gates, and the next execution step, and local docs/code do not contradict it, answer that no more discussion is needed.
- Classify the documentation target before proposing updates: plans and ADRs answer different questions, and some tasks legitimately need both.
When the user asks whether remaining questions exist, answer the yes/no first. Only ask a batch if at least one unresolved question would materially change the plan, contract, public/private boundary, or acceptance gate.
Convergence Loop
This skill should remove the burden of asking "are we done yet?" from the user. After every accepted batch, do the loop yourself:
- Interpret the user's reply, including shorthand such as "LGTM", "all agree", "others are fine", "2 no because...", or "do it".
- Apply the resolved updates to the plan, context doc, or ADR surface named in the batch. If no document update is warranted, say why.
- Re-read the updated target and run a fresh saturation audit.
- Either ask the next material batch or stop with the no-more-discussion response.
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 · 227 lines · 72 tokens per session scan A d22f17a49ba8
grill-with-docs-batch is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 2,279 once invoked, about $0.0004 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
release
Create a new release with version bump, release notes, commit, and tag.
sub-audit
Run a code review and documentation audit on recent changes. Finds bugs, edge cases, missing docs, and type safety issues.
sub-docs
Sync all SubFrame documentation after feature work. Updates AGENTS.md lists, changelog, PROJECTNOTES decisions, and STRUCTURE.json.
sub-ipc
Regenerate the IPC channel reference documentation from ipcChannels.ts type maps.
sub-tasks
View and manage SubFrame Sub-Tasks. Use when starting work, completing tasks, checking what's pending, or creating new tasks from conversation.
onboard
Analyze project intelligence files and bootstrap SubFrame's STRUCTURE.json, PROJECTNOTES.md, and initial sub-tasks from existing codebase context.