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 agentmods add skills/coldmint9/synax/wiki-authoringnpx skills add coldmint9/Synax --skill wiki-authoringgit clone --depth 1 https://github.com/coldmint9/SynaxWrote 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/coldmint9/synax/wiki-authoring)<a href="https://agentmods.dev/skills/coldmint9/synax/wiki-authoring"><img src="https://agentmods.dev/badge/skills/coldmint9/synax/wiki-authoring.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.03415 |
| Opus 5 | $0.00011 | $0.01707 |
| Sonnet 5 | $0.00004 | $0.00683 |
| Haiku 4.5 | $0.00002 | $0.00342 |
Grade A, and why
wiki-authoring 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 4d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Authoring
You are writing an internal design document for a new teammate: a competent engineer who knows general software concepts but knows nothing about this project's names, abbreviations, or conventions.
They must be able to read your document top to bottom and understand the subsystem without opening the source first. If they have to already know the codebase to parse your first paragraph, the document has failed — no matter how accurate it is.
Reader contract (non-negotiable)
- Plain-language entry. The first paragraph after
## Overviewmust answer three things using no project-specific proper nouns: what this is, what problem it solves, and who or what depends on it. Save type names, file paths, and internal jargon for the paragraphs after it. - Explain a term the first time it appears. Any project-specific noun — a type, a subsystem, an internal concept, an abbreviation — gets a one-clause gloss on first use.
AgentLoopRuntime(一个会话一个实例的编排器) is enough. Never gloss the same term twice. - Progressive order. Within the document and within each
##section: what it is → why it exists → how it works → where it breaks. Do not open with an interface dump. - One idea per sentence. If a sentence has three clauses and four inline identifiers, split it. Density is not depth.
Depth bar
Readability is the floor, not the ceiling. Still required:
- Every
##section needs at least one substantive prose paragraph — concrete mechanisms, not a single line or a bare bullet dump. - Answer every keyQuestion from the outline explicitly. If a question has no answer in the code, say what is missing and name what you checked.
- Prefer showing interfaces (fenced code), state machines (tables or mermaid), and runtime behavior over merely naming files.
- Every major claim is traceable: inline backticks, a Source line after code fences, and matching entries in
references[]. - Explain WHY the design exists, HOW it behaves at runtime, WHAT breaks if misused.
- Never invent a type, function, or config key that is not in Code Context or a file you actually read.
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.
- 4d ago First seen · 294 lines · 22 tokens per session scan A 00acef43229c
wiki-authoring is a skill published in the GitHub repository coldmint9/Synax (11 stars, last pushed 20d ago), licensed MIT. It adds 22 tokens to every session and 3,415 once invoked, about $0.0001 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.
Other skills, from other repositories
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
surprise-me
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for…