deep-cast

deep-cast is a command for Claude Code from dotoricode/tink-harness. It costs 16 tokens per session (12,802 once invoked), scanned B, a copy of cast, MIT.

A command that conducts a detailed interview about a coding task and turns the answers into a work plan. It runs in deep mode for that request without changing the project's default settings.

In plain words
What is it for?
Use it before a complex task when you need to clarify the work, select a suitable harness, create a run plan, and begin the first approved safe step.
Why use it?
It helps choose an appropriate set of tools and working steps before coding begins. It also requires the work to start, asks one necessary question, or stops if you decide not to continue.

Command for Claude Code

Part of the tink plugin — 9 skills, 9 commands, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/dotoricode/tink-harness/deep-cast
Clone the repo
git clone --depth 1 https://github.com/dotoricode/tink-harness

Made for: Claude Code.

Or install tink, the plugin that ships this one along with the rest of its 9 skills, 9 commands, 1 hook.

Wrote 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.

agentmods badge for deep-cast

README.md
[![agentmods](https://agentmods.dev/badge/commands/dotoricode/tink-harness/deep-cast.svg)](https://agentmods.dev/commands/dotoricode/tink-harness/deep-cast)
Your own site
<a href="https://agentmods.dev/commands/dotoricode/tink-harness/deep-cast"><img src="https://agentmods.dev/badge/commands/dotoricode/tink-harness/deep-cast.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 12,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.12802
Opus 5 $0.00008 $0.06401
Sonnet 5 $0.00003 $0.02560
Haiku 4.5 $0.00002 $0.01280

Measured 3d ago against content hash 9128e112e9c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

deep-cast scanned grade B with 1 finding 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 3d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

If legacy Tiny files such as `.tiny/` or `/tiny:use` instructions are present, treat them as old state. Explain that `/tink:cast` replaces `/tiny:use`, and offer to migrate useful `.tiny/harnesses/`, `.tiny/config.json`,
Origin

This is a copy

88% identical to cast — 252 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/tink/deep-cast.md · 826 lines

How it starts

The opening of the file, as written. The whole thing — 826 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tink:deep-cast

Always runs in deep mode regardless of cast_mode in .tink/config.json. Does not modify config.json. Use this for one-shot deep interviews without changing your default cast mode.

deep-cast is /tink:cast with deep mode forced for this invocation only.

Product promise

Tink is not a harness recommendation list. It must leave the user with an active run state and a concrete next action.

Tink should:

  1. understand the task,
  2. choose the smallest effective harness/tool set,
  3. replace heavy harnesses when the current stage or token budget makes them harmful,
  4. build or synthesize a narrow harness when none fits,
  5. materialize the harness as a run plan,
  6. execute the first safe step after approval,
  7. prevent repeated mistakes while working,
  8. maintain the harness set through approved memory, weave, or frog proposals.

Default behavior

Do not stop after saying which harness might fit.

A valid /tink:deep-cast response must do one of these:

  • create or update .tink/current/ and start the harnessed work,
  • ask one blocking question that is required to create .tink/current/, or
  • cancel because the user chose not to proceed.

This command always runs the Deep mode interview. Lane 1 and Lane 2 fast paths do not apply. After the interview produces a spec, proceed to the full Procedure.

Interaction policy

Always call the AskUserQuestion tool for choice prompts. Do not render text format. Do not ask the user to type a number inline.

Map prompt content to AskUserQuestion fields:

  • question: the full question text
  • header: max 12-character tag (e.g. "진행 방식", "하네스 선택", "Git 설정")
  • label: 1–5 word option name (e.g. "승인", "조정", "취소"). Add "(권장)" to the first option label if it is recommended.
  • description: explanatory text for the option

Label quality rules:

  • Use short, common, readable labels only. Good Korean labels are 승인, 조정, 취소, 요구사항 입력, 기본 절차만 사용, 새 하네스 초안 만들기, 구조 점검, 내용 점검, 전체 점검.
  • Do not invent compressed Korean labels, transliterated fragments, or unclear summaries such as 콘데의달 지질.
  • If the idea is too specific for a clean 1-5 word label, put the detail in description and use a generic label such as 내용 점검 or 전체 점검.
  • Before calling AskUserQuestion, reread each Korean label. If it looks misspelled, unnatural, or semantically unclear, replace it with a plain fallback label.

Read the full file on GitHub · 826 lines

Changes

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.

  1. 3d ago First seen · 826 lines · 16 tokens per session scan B 9128e112e9c4

Subscribe to this mod's changes

deep-cast is a command published in the GitHub repository dotoricode/tink-harness (1 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 12,802 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). It is 88% identical to cast, differing in 252 lines, and is treated as a copy.