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.
curl -O https://raw.githubusercontent.com/jakubsuplicki/codument/main/.agents/skills/grill-with-docs/SKILL.mdgit clone --depth 1 https://github.com/jakubsuplicki/codumentWrote 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/jakubsuplicki/codument/grill-with-docs)<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>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 | $0.00036 | $0.00760 |
| Opus 5 | $0.00018 | $0.00380 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
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.
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
- Load the smallest relevant context:
AGENTS.mdor the active agent instruction filedocs/overview.mddocs/.registry.json- relevant
docs/features/*.md - relevant
docs/concepts/*.md - relevant ADRs under
docs/architecture/decisions/
- Inspect code when docs can answer only part of the question.
- Ask one sharp question at a time when a real product or architecture decision remains.
- Lead with your recommended answer and the one reason that decides it.
- 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.
- Update the narrowest durable doc only after decisions settle, unless the user is explicitly brainstorming without file edits.
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.
- 7d ago First seen · 58 lines · 36 tokens per session scan A fc4abf583258
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.
Other skills, from other repositories
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
e2e
Generate and run Playwright E2E tests traced to spec.md acceptance criteria, with an optional accessibility audit. Use when saying "e2e tests" or "a11y audit".
release-expert
Multi-repo release coordination: version alignment, RC lifecycle, release waves, rollback planning. Use when saying "release", "version alignment", or "cut an RC".
tdd-cycle
Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
debug
Systematic 4-phase debugging with escalation protocol. Use when saying "debug", "investigate bug", "find root cause", "why is this failing", or "fix this bug".
increment
Plan a unit of work as a SpecWeave increment - spec.md with Problem, Scope, numbered ACs and an Approach, plus tasks.md. Use when starting a feature, bug, hotfix or refactor.