grill

grill is a skill for Claude Code, Codex from SpaiR/task-pipeline. It costs 33 tokens per session (2,046 once invoked), scanned A, original, MIT.

A guided question-and-answer step for examining a plan or decision before recording it. It keeps a list of decisions and the reasons behind them, then prepares the discussion for another tool to save.

In plain words
What is it for?
Use it to test ideas such as a retry design or queue sharding choice. It asks questions one at a time and ends with a pre-mortem, which considers how the plan could fail.
Why use it?
It helps expose weak assumptions and missing risks before a plan becomes fixed. It also preserves why each decision was made, so that reasoning is not lost.

Skill for Claude CodeCodex

Part of the task plugin — 8 skills, 8 agents shipped together

Install

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.

agentmods
npx agentmods add skills/spair/task-pipeline/grill
Any agent
npx skills add SpaiR/task-pipeline --skill grill
Clone the repo
git clone --depth 1 https://github.com/SpaiR/task-pipeline

Made for: Claude Code, Codex.

Or install task, the plugin that ships this one along with the rest of its 8 skills, 8 agents.

Wrote 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.

agentmods badge for grill

README.md
[![agentmods](https://agentmods.dev/badge/skills/spair/task-pipeline/grill.svg)](https://agentmods.dev/skills/spair/task-pipeline/grill)
Your own site
<a href="https://agentmods.dev/skills/spair/task-pipeline/grill"><img src="https://agentmods.dev/badge/skills/spair/task-pipeline/grill.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.02046
Opus 5 $0.00016 $0.01023
Sonnet 5 $0.00007 $0.00409
Haiku 4.5 $0.00003 $0.00205

Measured 5d ago against content hash c4035a1b33e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grill 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.

skills/grill/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pressure-test a plan, decision, or idea before it is frozen into an artifact. grill sits at the pipeline's first stage — "discuss freely in chat" — and gives it teeth: it interrogates the thinking one question at a time, records every answer as a decision with its rationale, closes with a pre-mortem, then hands off to the right capture skill. It writes nothing; its output is a hardened discussion plus a decision ledger that a to-* skill then serializes.

Input: $ARGUMENTS — optional. A topic or free-form context to grill (e.g. "the retry design", "whether to shard the queue"). Empty → grill the plan/decision being discussed in the current chat.

No setup gate, no setup. grill reads nothing under .task/.task/CLAUDE.md included, so the platform never auto-loads it here — so it runs in a fresh, unconfigured project before any capture exists. Dialog mirrors the language of the chat; facts are looked up with plain tools (Read / Grep / Glob / Bash).

Step 1: Frame what is being grilled

State, in 1–3 sentences, the plan/decision/idea as you currently understand it — from $ARGUMENTS if given, else from the chat. This is the target the questions attack. Do not ask the user to confirm the framing with a separate prompt; the first question implicitly tests it.

Step 2: Resolve facts lazily, ask only decisions

Split what stands between you and the next question into two piles:

  • Facts — anything the environment can answer: what a file does, whether a library is already a dependency, how an existing flow behaves. Look these up yourself with Read / Grep / Glob / Bash. Never ask the user a question the repo already answers.
  • Decisions — genuine choices with trade-offs, no single right answer derivable from the environment. These, and only these, are what you ask.

Resolve facts lazily — only the ones that gate the next question, not everything up front — so the first question reaches the user fast. When several independent reads are needed for one question, batch them in parallel. If a supposed decision turns out to have a factual answer, resolve it silently and move on — don't burn a question on it.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 5d ago First seen · 94 lines · 33 tokens per session scan A c4035a1b33e6

Subscribe to this mod's changes

grill is a skill published in the GitHub repository SpaiR/task-pipeline (7 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 2,046 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 2026-08-31.

Related

Other skills, from other repositories

errata

Correct what was written wrong — the binding line rewritten in place, the record it came from appended to and never touched, both carrying the evidence that overturned it. Use when a run, a file, or the user contradicts something already written in a work file, a plan's contract, the glossary, or the decision index…

donald-ada/workinggenius · 92 tokens

setup-working-genius

Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.

donald-ada/workinggenius · 43 tokens

decision-record

Keep the index of the project's settled decisions in .genius/DECIDED.md — one line per decision, pointing at the fight that settled it, earned by one test: would a future stranger re-fight this? Use when such a decision lands, when a design might contradict a settled one, or when another skill needs the index…

donald-ada/workinggenius · 73 tokens

domain-glossary

Maintain the project's shared vocabulary in CONTEXT.md — challenge conflicting terms, sharpen fuzzy language, record resolutions inline. Use when a term conflicts with or is missing from the glossary, when a decision names a new concept, or when another skill needs the glossary discipline.

donald-ada/workinggenius · 57 tokens

dw-grain

Audit code just written for excess the gate cannot see: a helper reinvented beside its canonical home, a wrapper with one caller, config for a case that never occurs, a shape the neighbouring files build differently, code this change stranded. One table, and every row is a deletion or a reuse. Explicit-invoke only.

dominikwozniak/dw-solo-skills · 69 tokens

dw-doctor

Read-only environment diagnostic for a solo-lane repo: whether the tools the hooks and skills assume are installed and whether the repo's guardrails will really fire, each gap reported with a copy-paste fix.

dominikwozniak/dw-solo-skills · 46 tokens