codument: Skill for Claude Code

.agents/skills/grill-with-docs/SKILL.md

grill-with-docs is a skill for Claude Code, Codex from jakubsuplicki/codument. It costs 36 tokens per session (760 once invoked), scanned A, original, Apache-2.0.

A guided investigation step for resolving important assumptions before planning or coding a change, using project documentation, architecture records, source mappings, and code.

In plain words
What is it for?
Use it when a requested change depends on an unresolved product, architecture, migration, compatibility, scope, or testing decision.
Why use it?
It helps settle unclear behavior, scope, design choices, affected parts, and verification requirements before implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is jakubsuplicki/codument's own configuration. It tells Claude Code and Codex how to work on codument itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codument configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jakubsuplicki/codument. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jakubsuplicki/codument/main/.agents/skills/grill-with-docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jakubsuplicki/codument

Made for: Claude Code, Codex.

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-with-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakubsuplicki/codument/grill-with-docs.svg)](https://agentmods.dev/skills/jakubsuplicki/codument/grill-with-docs)
Your own site
<a href="https://agentmods.dev/skills/jakubsuplicki/codument/grill-with-docs"><img src="https://agentmods.dev/badge/skills/jakubsuplicki/codument/grill-with-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.00760
Opus 5 $0.00018 $0.00380
Sonnet 5 $0.00007 $0.00152
Haiku 4.5 $0.00004 $0.00076

Measured 7d ago against content hash fc4abf583258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 7d 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.

.agents/skills/grill-with-docs/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill With Docs

Use this before implementation, when a change turns on a load-bearing assumption that one line can't settle — a rough idea, an ambiguous change, or a "before we code" direction that's still open. It's the deep-dive the assumption gate routes into when surfacing the assumption with a recommended reading isn't enough on its own.

Boundary With Plan With Docs

grill-with-docs is for deciding what the work should be. plan-with-docs is for writing the agreed implementation plan after the important decisions are settled.

Stay in grill-with-docs when any meaningful boundary is still unresolved:

  • product behavior, user workflow, or success criteria
  • architecture, migration, compatibility, or data-shape tradeoffs
  • scope, non-goals, rollout, or reversibility
  • affected callers, docs, tests, or dependent features
  • verification strategy or acceptance criteria
  • the right durable doc home for the decision

If the user asks to "plan" but these decisions are still open, say so in a line. Ask one sharp decision question, lead with your recommended answer and the one reason that decides it, then wait for the user's decision before turning it into a plan.

Workflow

  1. Load the smallest relevant context:
    • AGENTS.md or the active agent instruction file
    • docs/overview.md
    • docs/.registry.json
    • relevant docs/features/*.md
    • relevant docs/concepts/*.md
    • relevant ADRs under docs/architecture/decisions/
  2. Inspect code when docs can answer only part of the question.
  3. Ask one sharp question at a time when a real product or architecture decision remains.
  4. Lead with your recommended answer and the one reason that decides it.
  5. Stress-test the answer against concrete scenarios, failure modes, and edge cases — in your head, before you write. Surface only a finding that would change the user's decision; the rest is yours to act on, not theirs to read.
  6. Update the narrowest durable doc only after decisions settle, unless the user is explicitly brainstorming without file edits.

Read the full file on GitHub · 58 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. 7d ago First seen · 58 lines · 36 tokens per session scan A fc4abf583258

Subscribe to this mod's changes

grill-with-docs is a skill published in the GitHub repository jakubsuplicki/codument (47 stars, last pushed 16d ago), licensed Apache-2.0. It adds 36 tokens to every session and 760 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.