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 stark-ai-de/agent-skills --skill grill-plangit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/grill-plan)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/grill-plan"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/grill-plan/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/stark-ai-de/agent-skills/grill-plan"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/grill-plan.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 | $0.00050 | $0.00674 |
| Opus 5 | $0.00025 | $0.00337 |
| Sonnet 5 | $0.00010 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
grill-plan 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 12d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Plan
Goal
Pressure-test a plan before execution so hidden assumptions, risky branches, missing approvals, and validation gaps become explicit decisions.
When to use
- The user asks to be grilled, challenged, or questioned before implementation.
- A migration, release, architecture change, or repo maintenance plan has unclear constraints.
- The user wants decision branches clarified before work starts.
When not to use
- Do not use when the user has already asked for implementation and the plan is clear.
- Do not use for passive code review; use the relevant review skill.
- Do not use to delay an urgent fix when the blocking decision is already known.
Inputs to inspect
- Inspect the plan, issue, PR, design doc, repo constraints, validation commands, and approval boundaries.
- Explore code or docs directly when a question can be answered from local evidence.
Inputs
- The proposed plan, design, checklist, issue, PR, or release notes.
- Repo constraints, workflow docs, validation commands, and known risks.
- User goals, deadlines, approval boundaries, and rollback expectations.
Process
- Restate the objective and the riskiest assumption.
- Ask focused questions that change the plan if answered differently.
- Group questions by decision branch, not by curiosity.
- Identify missing evidence, approvals, rollback plans, and validation.
- Convert answers into a tightened plan or explicit blockers.
- Stop when the next action is clear enough to execute or reject.
Workflow
Use the process above, asking one high-leverage question at a time. End with a tightened plan, explicit blockers, or a decision that implementation should not proceed.
Decision points
- If a question does not change the plan, omit it.
- If the plan can fail irreversibly, require an approval and rollback answer.
- If uncertainty is acceptable, mark it as a conscious risk instead of blocking.
Safety rules
- Do not perform implementation while grilling unless the user switches modes.
- Do not overwhelm the user with a long questionnaire; ask the highest-leverage questions first.
- Do not treat assumptions as decisions.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 95 lines · 50 tokens per session scan A dccc8b38b11e
grill-plan is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 674 once invoked, about $0.0003 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.
Other skills, from other repositories
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-plan-refactor
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-implement-story
Implement a brownfield story with OpenLore orientation, risk checks, spec validation, tests, and drift detection. Use when asked to implement or continue a story in an existing codebase.
openlore-write-tests
Write and run real tests for a function or spec scenario after reading implementation and contract evidence. Use when asked to add, improve, or repair tests without stubs or placeholders.