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/castgit clone --depth 1 https://github.com/dotoricode/tink-harnessWhat 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 | $0.00015 | $0.15457 |
| Opus 5 | $0.00008 | $0.07729 |
| Sonnet 5 | $0.00003 | $0.03091 |
| Haiku 4.5 | $0.00002 | $0.01546 |
Grade B, and why
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 2d 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`, Copies of this mod
1 near-identical copy found in the catalogue:
- deep-cast — 88% identical, 252 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,028 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tink:cast
Cast the right harness for the task, run it, and capture reusable learning.
cast is the main Tink command. Use it before non-trivial work.
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:cast response must do one of these:
- complete a clearly simple, safe task directly through the quick-triage fast path (Lane 1 below) - work starts in the same response,
- 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.
If the task is clear enough to classify, do not ask broad clarification first. Make a best recommendation, ask for approval, then act.
Cast mode
/tink:cast without a task argument shows the current mode and the description of all three modes directly — no change prompt, just information. /tink:cast <mode> sets the mode and saves it to cast_mode in .tink/config.json with a single confirmation line and no Lane 1 framing.
Modes:
quick— Forces Lane 1 fast path regardless of task complexity. Skips harness selection and starts immediately.standard— Default behavior. Quick triage selects the right lane automatically.deep— Runs a structured interview before planning. See Deep mode below.
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.
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.
- 2d ago First seen · 1,028 lines · 15 tokens per session scan B 91c5f489a334
cast is a command published in the GitHub repository dotoricode/tink-harness (1 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 15,457 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
audit-codebase
RTK Codebase Health Audit — 7 catégories scorées 0-10.
test-routing
Test RTK command routing without execution (dry-run) - verifies which commands have filters.
clean-worktrees
Clean all merged worktrees automatically (no interaction).
audit-repo-docs
Audit repository documentation against 85+ best practices from claude-code-ultimate-guide.
release
Release guide version (CHANGELOG + VERSION + README + landing sync + commit + push).
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.