bifrost: Skill for Codex

.agents/skills/zhihu-publish/SKILL.md

zhihu-publish is a skill for Codex from bifrost-proxy/bifrost. It costs 89 tokens per session (1,383 once invoked), scanned A, original, MIT.

A tool for publishing Markdown articles to Zhihu Columns, a Chinese platform for long-form posts, and verifying the resulting page.

In plain words
What is it for?
It helps prepare, preview, save as drafts, publish, repost, and check Zhihu articles with text, links, images, and code.
Why use it?
It removes the need for browser-based publishing and helps prevent duplicate or incorrectly formatted posts.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is bifrost-proxy/bifrost's own configuration. It tells Codex how to work on bifrost itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bifrost configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/eden_studio/.codex/skills/.system/skill-creator/scripts/quick_validate.py.

Reuse

Borrowing it

Nothing to install: this file belongs to bifrost-proxy/bifrost. 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/bifrost-proxy/bifrost/main/.agents/skills/zhihu-publish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bifrost-proxy/bifrost

Made for: Codex.

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.

agentmods badge for zhihu-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/bifrost-proxy/bifrost/zhihu-publish/github.svg)](https://agentmods.dev/skills/bifrost-proxy/bifrost/zhihu-publish)
Your own site
<a href="https://agentmods.dev/skills/bifrost-proxy/bifrost/zhihu-publish"><img src="https://agentmods.dev/badge/skills/bifrost-proxy/bifrost/zhihu-publish/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.

agentmods 80×15 button for zhihu-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/bifrost-proxy/bifrost/zhihu-publish"><img src="https://agentmods.dev/badge/skills/bifrost-proxy/bifrost/zhihu-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.01383
Opus 5 $0.00044 $0.00691
Sonnet 5 $0.00018 $0.00277
Haiku 4.5 $0.00009 $0.00138

Measured 9d ago against content hash da61536cce17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

zhihu-publish 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 9d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/zhihu-publish.mjs, scripts/zhihu-publish.test.mjs, scripts/zhihu-verify.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/zhihu-publish/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zhihu Publish

Use the bundled scripts for deterministic publishing. Do not operate Chrome or another browser through UI automation. Read only authentication and endpoint-specific signing context from Bifrost traffic. The stable publish payload schema is built into the script; never read a captured request body as a reusable template.

Never print or save Cookie values, XSRF tokens, x-zse-*, x-zst-*, raw request headers, or unredacted Bifrost traffic.

Prepare the article

Copy article.template.md and fill title. The remaining fields are optional.

  • Start the body with the introduction or an H2; do not repeat the title as an H1.
  • Keep one source file per intended article so duplicate prevention remains stable.
  • Existing frontmatter fields for another platform are allowed and ignored.
  • The renderer supports headings, paragraphs, lists, links, images, inline code, fenced code blocks, blockquotes, emphasis, and horizontal rules.
  • Images may use HTTP(S), a local JPEG/PNG/GIF/WebP/BMP path relative to the article, an absolute local image path, or a matching base64 data URI. Live writes transfer every non-Zhihu image to Zhihu first; SVG and files over 20 MiB are rejected.

Read traffic-contract.md only when diagnosing a Zhihu API or capture change.

Preview

Always run a dry run before a live write:

.agents/skills/zhihu-publish/scripts/zhihu-publish \
  --article /absolute/path/article.md \
  --dry-run

Confirm the title, Markdown/HTML character counts, action, duplicate state, and image counts. Dry-run never uploads an image.

Check the captured authentication/signing state without exposing credentials:

.agents/skills/zhihu-publish/scripts/zhihu-publish --check-auth

Save a draft or publish

Use --draft-only for a Zhihu draft. Use --publish only when the user explicitly requests publication.

.agents/skills/zhihu-publish/scripts/zhihu-publish \
  --article /absolute/path/article.md \
  --draft-only

.agents/skills/zhihu-publish/scripts/zhihu-publish \
  --article /absolute/path/article.md \
  --publish

Read the full file on GitHub · 128 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. 9d ago First seen · 128 lines · 89 tokens per session scan A da61536cce17

Subscribe to this mod's changes

zhihu-publish is a skill published in the GitHub repository bifrost-proxy/bifrost (132 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 1,383 once invoked, about $0.0004 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.