Borrowing it
Nothing to install: this file belongs to smileynet/teach-me. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/smileynet/teach-me/main/.kiro/steering/ink-authoring.mdgit clone --depth 1 https://github.com/smileynet/teach-meWrote 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/instructions/smileynet/teach-me/ink-authoring)<a href="https://agentmods.dev/instructions/smileynet/teach-me/ink-authoring"><img src="https://agentmods.dev/badge/instructions/smileynet/teach-me/ink-authoring.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 5.1 | $0.01609 | $0.01609 |
| Opus 5 | $0.00805 | $0.00805 |
| Sonnet 5 | $0.00322 | $0.00322 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
teach-me ink-authoring.md 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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ink Authoring Correctness
Guidance for writing ink narrative stories and lesson code fragments that are
not just syntactically valid but produce correct output. The reference
stories in ink-test-project/stories/ and the ink-godot lessons already follow
these rules — this documents the standard and the tooling that enforces it.
The core principle
"Compiles + reaches END" ≠ "produces correct output." A story can compile
cleanly, pass playthrough (reach an ending), survive subagent review, and still
print the wrong text. Three bug classes (below) are invisible to structural
validation — they were caught historically only by a human reading the output.
The golden-transcript check (mise run ink:transcripts) is the mechanism that
catches them automatically.
The three correctness rules
1. Test a knot's read count from OUTSIDE, never self-loop
A knot's read count reflects entry, not internal passes. A condition that tests the enclosing knot's own count inside a self-loop never advances:
// WRONG — {shop} counts entries; self-loop never increments it
=== shop ===
{shop == 1: First visit!|Welcome back.}
+ [Look around] -> shop // re-enters via divert, but count is stuck
Two correct patterns:
- Hub-and-spoke — divert out to a hub, re-enter the counted knot via a
fresh divert (read count advances on each fresh entry). This is what the
reference stories use (
well→village→well). - Explicit VAR counter —
~ visits = visits + 1on each pass, branch on the variable, not the read count.
2. Choices in re-enterable locations must be sticky (+) or have a fallback
A once-only choice (* [text]) in a knot the player can re-enter (via loop-back
or tunnel) is exhausted on re-entry. Without a sticky choice or an unconditional
gather to fall through to, the player is stranded ("ran out of content"):
= weapons
* "Show me your swords." -> weapons.shown // once-only dialogue — fine
+ [Leave] -> market_square // STICKY fallback — keeps loop alive
- -> market_square // gather also catches fall-through
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.
- yesterday First seen · 133 lines · 1,609 tokens per session scan A 18315f5437fd
teach-me ink-authoring.md is an instructions file published in the GitHub repository smileynet/teach-me (3 stars, last pushed today), licensed MIT. It adds 1,609 tokens to every session, about $0.0080 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 2026-09-06.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.