agentmods.dev

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.

In plain words
What is it for?
Use them to install dependencies, run checks and tests, execute the full or partial pipeline, and generate documentation or skill files.
Why use it?
They help contributors run the project consistently and preserve the required order of checking, testing, fetching, analyzing, and generating output.

Instructions file for CodexOpenCode

16 3d ago A scan 1,318 tokens original MIT
View the source file ChouChiu/heya-skill
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 instructions/chouchiu/heya-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/ChouChiu/heya-skill

Made for: Codex, OpenCode.

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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01318 $0.01318
Opus 5 $0.00659 $0.00659
Sonnet 5 $0.00264 $0.00264
Haiku 4.5 $0.00132 $0.00132

Measured 3d ago against content hash a893dbe5410c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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 <!-- AUTO_START:xxx --> / <!-- AUTO_END:xxx --> 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.

  1. 3d 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 (16 stars, last pushed 3d ago), licensed MIT. It adds 1,318 tokens to every session, about $0.0066 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 2026-08-30.

Creative and mediaagentsawesome-skillsheyaskillskills
Related

Other instructions, from other repositories

Loop AGENTS.md

Instructions for Kevin-Liu-01/Loop, covering claude code prompt for plan mode, ultracite code standards, quick reference, core principles and type safety & explicitness.

Kevin-Liu-01/Loop · 1,953 tokens

agentic-workflow CLAUDE.md

Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.

gtrabanco/agentic-workflow · 4,297 tokens

skills AGENTS.md

Instructions for flc1125/skills, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

flc1125/skills · 662 tokens

autovault CLAUDE.md

Instructions for autoworks-ai/autovault, covering claude.md, project, common commands, architecture and request flow.

autoworks-ai/autovault · 1,660 tokens

SonarCloud-Skill-Agent-Guidance

Repository guidance for the SonarCloud/SonarQube findings management skill.

Nick2bad4u/SonarCloud-Skill · 435 tokens

claude-for-strategy CLAUDE.md

Instructions for daddia/claude-for-strategy, covering claude.md, layout, validation — run before opening a pr, 2. json sanity and 3. consulting reference mirrors.

daddia/claude-for-strategy · 2,094 tokens