Borrowing it
Nothing to install: this file belongs to FerryCorleone/pingshu-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.
curl -O https://raw.githubusercontent.com/FerryCorleone/pingshu-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/FerryCorleone/pingshu-skillWrote 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/ferrycorleone/pingshu-skill/agents-md)<a href="https://agentmods.dev/instructions/ferrycorleone/pingshu-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/ferrycorleone/pingshu-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.
<a href="https://agentmods.dev/instructions/ferrycorleone/pingshu-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/ferrycorleone/pingshu-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00389 | $0.00389 |
| Opus 5.5 | $0.00156 | $0.00156 |
| Sonnet 5.5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
pingshu-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.
What it actually says
AGENTS.md
Project Intent
This repository builds pingshu-skill, a portable Agent Skill that turns sourced story material into respectful Chinese pingshu-style scripts and provider-neutral TTS performance plans.
The goal is not to parody or replace traditional pingshu artists. Treat pingshu as a living performance tradition: preserve respect for its craft, cite sources, avoid voice impersonation, and make modern adaptations clearly transformative.
Working Rules
- Keep the skill usable by different agents and operating systems. Prefer plain Markdown, JSON, and Node.js scripts without native dependencies.
- Do not require macOS-only tools, shell-specific behavior, or browser automation for the core workflow.
- Keep
pingshu-skill/SKILL.mdconcise. Put detailed knowledge inpingshu-skill/references/. - Use structured intermediate artifacts:
story_pack.jsonpingshu_script.jsonperformance_plan.json
- Do not let the skill fabricate source facts when the user asks for an existing work, episode, event, or scene. If sources are weak, mark uncertainty and ask for or gather better material.
- Do not clone, imitate, or suggest imitating a real living artist's voice without explicit permission. Use original character voices or properly licensed voices.
- Do not directly rewrite another creator's recap as if it were raw story fact. Use recaps as leads only, then corroborate or cite them.
Development Checks
Run these before claiming the skill is ready:
python3 "${CODEX_HOME:-$HOME/.codex}/skills/.system/skill-creator/scripts/quick_validate.py" pingshu-skill
node pingshu-skill/scripts/validate_skill_outputs.mjs examples
git status --short
If Node is unavailable, the Markdown skill remains usable, but the bundled scripts have not been verified.
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 · 33 lines · 389 tokens per session scan A c2a0b53bfee5
pingshu-skill AGENTS.md is an instructions file published in the GitHub repository FerryCorleone/pingshu-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 389 tokens to every session, about $0.0016 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 2026-08-31.
pingshu-skill AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pingshu-skill AGENTS.mdFerryCorleone/pingshu-skill | Instructions file | 5 | 4mo ago | MIT | A | 389 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |