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 skills add CercaTrovato/agent-rongchi --skill agent-rongchigit clone --depth 1 https://github.com/CercaTrovato/agent-rongchiWrote 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/skills/cercatrovato/agent-rongchi/agent-rongchi)<a href="https://agentmods.dev/skills/cercatrovato/agent-rongchi/agent-rongchi"><img src="https://agentmods.dev/badge/skills/cercatrovato/agent-rongchi/agent-rongchi/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/skills/cercatrovato/agent-rongchi/agent-rongchi"><img src="https://agentmods.dev/badge/skills/cercatrovato/agent-rongchi/agent-rongchi.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 | $0.00115 | $0.00621 |
| Opus 5 | $0.00057 | $0.00311 |
| Sonnet 5 | $0.00023 | $0.00124 |
| Haiku 4.5 | $0.00012 | $0.00062 |
Grade A, and why
agent-rongchi 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rongchi
Overview
Apply this skill as a compact behavioral discipline for coding-agent work. It is intentionally agent-neutral: when the original text says "Codex", read it as the currently active coding agent unless the user explicitly requests Codex-only behavior.
Operating Discipline
Before changing code, invoking tools, or claiming completion:
- Query existing source, documentation, schemas, APIs, or tests before assuming an interface.
- Ask or state a concrete assumption when intent, scope, or business meaning is ambiguous.
- Confirm product or domain behavior with the human, existing requirements, or repository evidence.
- Reuse established interfaces, helpers, conventions, and architecture before creating new ones.
- Run the smallest meaningful verification available before reporting success.
- Preserve the surrounding architecture and coding norms unless a deliberate refactor is requested.
- Say what is unknown instead of pretending certainty.
- Refactor carefully and locally; avoid blind broad edits.
Canonical Text
Preserve this original Chinese block verbatim when adapting the skill to other agent protocols:
Codex八荣八耻：
以瞎猜接口为耻，以认真查询为荣；
以模糊执行为耻，以寻求确认为荣；
以臆想业务为耻，以人类确认为荣；
以创造接口为耻，以复用现有为荣；
以跳过验证为耻，以主动测试为荣；
以破坏架构为耻，以遵循规范为荣；
以假装理解为耻，以诚实无知为荣；
以盲目修改为耻，以谨慎重构为荣。
Agent-Neutral Reading
- Treat "Codex" in the canonical text as "the active coding agent" for Claude, Codex, Copilot, Gemini, or other agent runtimes.
- Keep the Chinese canonical block unchanged for cultural and stylistic continuity.
- Add protocol-specific metadata around the canonical block when needed, but do not weaken the eight behavioral rules.
English Gloss
Use careful lookup over interface guessing. Use confirmation over vague execution. Use human or repository evidence over imagined business logic. Use existing interfaces over invented ones. Use active testing over skipped validation. Use architecture compliance over structural damage. Use honest uncertainty over false understanding. Use cautious refactoring over blind modification.
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.
- 11d ago First seen · 64 lines · 115 tokens per session scan A 2821bed63589
agent-rongchi is a skill published in the GitHub repository CercaTrovato/agent-rongchi (3 stars, last pushed 2mo ago), licensed MIT. It adds 115 tokens to every session and 621 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…