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 commands/dotoricode/tink-harness/deep-castgit clone --depth 1 https://github.com/dotoricode/tink-harnessWrote 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/dotoricode/tink-harness/deep-cast)<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>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 | $0.00016 | $0.12802 |
| Opus 5 | $0.00008 | $0.06401 |
| Sonnet 5 | $0.00003 | $0.02560 |
| Haiku 4.5 | $0.00002 | $0.01280 |
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`, 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.
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:
- understand the task,
- choose the smallest effective harness/tool set,
- replace heavy harnesses when the current stage or token budget makes them harmful,
- build or synthesize a narrow harness when none fits,
- materialize the harness as a run plan,
- execute the first safe step after approval,
- prevent repeated mistakes while working,
- 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 textheader: 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
descriptionand use a generic label such as내용 점검or전체 점검. - Before calling
AskUserQuestion, reread each Korean label. If it looks misspelled, unnatural, or semantically unclear, replace it with a plain fallback label.
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.
- 3d ago First seen · 826 lines · 16 tokens per session scan B 9128e112e9c4
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.
Other commands, from other repositories
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
review
Code review with security and @MX tag compliance check.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
version
Display current guide and Claude Code versions.