What is heya-skill AGENTS.md?

Repository instructions for a Bun-based tool that creates title styles for Bilibili videos, a Chinese video platform, using a fetch, analysis, and generation pipeline. They define its commands, runtime, and development checks.

Use them to install dependencies, run checks and tests, execute the full or partial pipeline, and generate documentation or skill files.

They help contributors run the project consistently and preserve the required order of checking, testing, fetching, analyzing, and generating output.

How ChouChiu/heya-skill configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ChouChiu/heya-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ChouChiu/heya-skill/v2/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ChouChiu/heya-skill

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/chouchiu/heya-skill/agents-md/github.svg)](https://agentmods.dev/instructions/chouchiu/heya-skill/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/chouchiu/heya-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/chouchiu/heya-skill/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/chouchiu/heya-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/chouchiu/heya-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,318 This file is loaded in full into every session.

When invoked 1,318 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.01318	$0.01318
Opus 5.5	$0.00527	$0.00527
Sonnet 5.5	$0.00264	$0.00264
Haiku 4.5	$0.00132	$0.00132

Measured 2mo ago against content hash a893dbe5410c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

heya-skill AGENTS.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 2mo 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.

AGENTS.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Bilibili creator "黑鸦" title style generator — CLI pipeline + AI skill output.

Runtime

Bun only. Every command uses bun. No npm/pnpm/yarn.
bun run <script> for package.json scripts, bun test for tests.
#!/usr/bin/env bun shebang on src/index.ts.

Commands

bun install                    # install deps (bun.lock)
bun run check                  # biome check . && tsc --noEmit
bun run format                 # biome check --write .
bun test                       # run all tests
bun test -t <pattern>          # filter by test name regex
bun run pipeline               # full pipeline: fetch → analyze → generate
bun run pipeline --skip-fetch --skip-analyze --dry-run
bun run docs                   # typedoc → docs/ (gitignored)

Order matters: bun run check before bun test. CI enforces this.

Pipeline

3 phases: fetch (UApi Bilibili proxy) → analyze (HanLP REST + deterministic aggregation) → generate (template substitution).

Fetch uses uapi-sdk-typescript — no Bilibili cookie or WBI signing needed. HanLP REST required for analysis; skip with --skip-analyze.

SKILL.md generation

Template: SKILL.template.md — the canonical source. Edit this file.
Output: skills/heya-title-style/SKILL.md — auto-generated from template + analysis, committed. This is the deployed agent skill artifact.
AUTO sections: Content between  /  is replaced by pipeline for these 4 sections: core-features, title-examples, vocab-library, structure-formulas. The core-guidance section has template fallback text but is NOT replaced by pipeline. Never edit AUTO sections in the output file.
Reference data: skills/heya-title-style/references/ is auto-generated.
- 00-llm-brief.md — compact LLM-readable summary
- 01-titles.csv — raw video titles
- 02-style-analysis.yaml — structured analysis data
- 02-style-analysis.md — human-readable analysis report
- 03-title-features.json — per-title debug data; never load wholesale into LLM context

Read the full file on GitHub · 110 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.

2mo ago First seen · 110 lines · 1,318 tokens per session scan A a893dbe5410c

Subscribe to this mod's changes

heya-skill AGENTS.md is an instructions file published in the GitHub repository ChouChiu/heya-skill (19 stars, last pushed yesterday), licensed MIT. It adds 1,318 tokens to every session, about $0.0053 per session on Opus 5.5. 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 2026-08-30.

TypeScript agents awesome-skills heya skill skills

heya-skill AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
heya-skill AGENTS.mdChouChiu/heya-skill	Instructions file	19	yesterday	MIT	A	1,318	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

heya-skill: Instructions file for Codex