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.
git clone --depth 1 https://github.com/adamwstauffer/shidlerWrote 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/commands/adamwstauffer/shidler/grill-me)<a href="https://agentmods.dev/commands/adamwstauffer/shidler/grill-me"><img src="https://agentmods.dev/badge/commands/adamwstauffer/shidler/grill-me/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/commands/adamwstauffer/shidler/grill-me"><img src="https://agentmods.dev/badge/commands/adamwstauffer/shidler/grill-me.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 | $0.00000 | $0.00577 |
| Opus 5 | $0.00000 | $0.00289 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
grill-me 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 9d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/grill-me [<artifact-or-scope>] — Ad-hoc pre-alignment grill
Run on demand before opening a brainstorming session, a docs/decisions/ memo, a course/stage restructure, or a rubric/template change. Converges decisions one branch at a time so the downstream brainstorm/memo/plan starts pre-aligned.
What this command does
You run as a sequential, one-question-at-a-time interrogator. You augment (do NOT replace) superpowers:brainstorming — your job is to converge decisions, not expand the option space.
Follow the methodology in .claude/skills/grill-me/SKILL.md end-to-end:
- One question at a time, with a recommended answer; pause for the human after every question.
- Before any structural recommendation (new course/project/stage/template, rubric/weight change, restructure, supersession), run the Auto-Pushback Pass (mandatory Pass 1 in an R-table; Pass 2 on the objective threshold; 2-pass cap — human pushback is Pass 3).
- Before any "new X" recommendation, run the Repo Convergence Check (grep
courses/,docs/templates/,docs/decisions/,_archive/— prefer extending an existing artifact; this repo's "no speculative restructuring" rule). - Force grading decisions through the grading-domain guardrails (generosity-only curve, no double-deductions, score privacy, GAAP/IFRS neutrality, Excel-formulas).
- When a hard-to-reverse call settles → propose a
docs/decisions/memo inline (hand to/decision-memo).
Argument
[<artifact-or-scope>] — Optional. Examples:
- A decision-memo draft:
docs/decisions/2026-07-12-foo.md - A stage doc or rubric:
courses/.../projects/fx-hedging/stage3-ai-build-audit.md - A restructure proposal pasted inline
- A free-form scope:
whether to split BUS-620 DLEMBA into its own subject dir
If no argument is given, ask what artifact or scope to grill before starting the core loop.
Exit
Stop and hand off when all in-scope decisions are resolved or deferred, the human says "good, let's brainstorm now" / "ship it", or three consecutive "defer" answers fire (recommend upstream research, then exit).
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.
- 9d ago First seen · 39 lines · 0 tokens per session scan A 016c4392a6c4
grill-me is a command published in the GitHub repository adamwstauffer/shidler (10 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 577 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.