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 ggemba/squad-mcp --skill grillmegit clone --depth 1 https://github.com/ggemba/squad-mcpWrote 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/ggemba/squad-mcp/grillme)<a href="https://agentmods.dev/skills/ggemba/squad-mcp/grillme"><img src="https://agentmods.dev/badge/skills/ggemba/squad-mcp/grillme/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/ggemba/squad-mcp/grillme"><img src="https://agentmods.dev/badge/skills/ggemba/squad-mcp/grillme.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 | $0.03673 |
| Opus 5 | $0.00000 | $0.01836 |
| Sonnet 5 | $0.00000 | $0.00735 |
| Haiku 4.5 | $0.00000 | $0.00367 |
Grade A, and why
grillme 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 8d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Grillme
Objective
Take the user's plan (a paragraph, a bullet list, a PRD-ish blurb — whatever) and run a Socratic interview that surfaces contradictions, sloppy terminology, and unstated decisions, one question at a time, grounded in the project's domain artefacts. When a term gets resolved or a decision gets made, capture it inline in CONTEXT.md and (sparingly) docs/adr/. The point is not to write code; it is to harden the plan before code gets written.
Position in the workflow:
/squad:brainstorm— explores what to build (outward research)/squad:grillme— interrogates a chosen plan against MY codebase (this skill)/squad:implement— writes the change
Inviolable Rules
- This skill writes user files. Unlike
brainstorm/debug/question/stats(read-only by rule),grillmemay mutateCONTEXT.md,CONTEXT-MAP.md, and files underdocs/adr/. Every write is preceded by an inline confirmation ("update CONTEXT.md to record this resolution?"). No silent writes. No writes to anything outside those three paths. Never edits source code. - No
git commit, nogit push. Read-only git is fine for context (git log,git status,git diff). The user owns the commit. - One question at a time. No question lists, no batching. Ask, wait for the answer, integrate it, then ask the next. The Socratic value comes from forcing depth on each branch before moving on.
- Recommend your answer. For every question, propose your best current answer so the user can correct rather than invent from scratch. Phrase: "I'd say X — does that match your model?"
- No AI attribution in any artifact produced.
CONTEXT.mdand ADR files must not carryCo-Authored-By: Claude / Anthropic / Generated with [...]lines. Consistent with the squad-wide commit-authorship rule. - ADRs are offered sparingly. Only when all three are true: (1) hard to reverse, (2) surprising without context, (3) the result of a real trade-off with rejected alternatives. If any one is missing, skip the ADR.
What ships with it
2 files 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.
- 8d ago First seen · 235 lines · 0 tokens per session scan A de0f531599d9
grillme is a skill published in the GitHub repository ggemba/squad-mcp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,673 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 skills, from other repositories
red-blue-review
An optional adversarial review process for requirement analyses. One agent produces the analysis, while an independent reviewer checks its report, database definitions, alignment records, and requirements for missed issues.
java-best-practices
Java coding best practices. Use when writing or reviewing Java code (17+). Covers modern features, error handling, and patterns.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this…
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.