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 agentmods add skills/control-decks/think-it-through/grillnpx skills add control-decks/think-it-through --skill grillgit clone --depth 1 https://github.com/control-decks/think-it-throughWrote 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/control-decks/think-it-through/grill)<a href="https://agentmods.dev/skills/control-decks/think-it-through/grill"><img src="https://agentmods.dev/badge/skills/control-decks/think-it-through/grill.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 | $0.00053 | $0.00431 |
| Opus 5 | $0.00026 | $0.00216 |
| Sonnet 5 | $0.00011 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
grill 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 5d 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.
What it actually says
🔥 Think Grill
ID: think-it-through/grill
HACP: 0.4
Kind: operation
Mode: transform
Traits: read-only, semantic, multi-exchange
Default Binding: Current proposal, assumption, decision, design, or plan
Accepts: hacp/content, hacp/result
Requires: hacp/testable-object
Produces: think-it-through/verdict
Duration: until-complete
Effect: Walk the bound object's decision tree, resolve discoverable facts, then test one unresolved branch at a time with a recommendation and demanding question.
Limits: Keep the selected Binding until verdict, stop, or redirection. Separate fact, inference, and unresolved claim. Do not decide for the human or ask for information available from sources you can inspect.
Flow
flowchart TD
A["Selected Binding"] --> B["Map decisions and dependencies"]
B --> C["Search available sources"]
C --> D["Choose weakest unresolved branch"]
D --> E["Give recommended answer"]
E --> F["Ask one demanding question"]
F --> G["Integrate the answer"]
G --> H{"Terminal result?"}
H -->|No| D
H -->|Yes| I["State verdict and remaining risks"]
Format
At launch, show the full trace: > 🎯 **<binding>** → 🔥 **GRILL**. On later turns, show > 🔥 **GRILL** · <binding>.
Show Recommendation, then Question. At completion, show Verdict and any remaining risks.
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.
- 5d ago First seen · 48 lines · 53 tokens per session scan A aa5c52aa60fb
grill is a skill published in the GitHub repository control-decks/think-it-through (3 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 431 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
claude-delegate
Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…
codex-delegate
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" …
commandcode-delegate
Delegate a coding task to the Command Code CLI (cmd) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code…
cursor-delegate
Delegate a coding task to the Cursor Agent CLI (cursor-agent) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use…
warp-delegate
Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…
zcode-delegate
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…