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 agents/landing-ai/ade-cli/writing-stylegit clone --depth 1 https://github.com/landing-ai/ade-cliWrote 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/agents/landing-ai/ade-cli/writing-style)<a href="https://agentmods.dev/agents/landing-ai/ade-cli/writing-style"><img src="https://agentmods.dev/badge/agents/landing-ai/ade-cli/writing-style.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 | $0.00000 | $0.00407 |
| Opus 5 | $0.00000 | $0.00204 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
writing-style 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.
What it actually says
Writing style
Standards for every string a user or an agent reads: help text and
docstrings (which become ade help and the hosted CLI reference), the
README, and SKILL.md.
Prose standards
- Second person ("you"), active voice, direct language.
- No promotional language. Describe what a thing does.
- No idioms. Plain wording wins.
- Cite what a reader outside this repo can open: public docs,
ade helptopics, and shipped flags. - Leave out issue numbers (enforced), internal URLs, and anything that resolves only inside LandingAI.
- Test every code example before it lands. Fence README and SKILL.md code blocks with a language tag.
- Error and status messages state what happened and what to do next.
Inline code is always backticked (enforced)
Wrap flags (--api-key), commands (ade update), paths
(~/.ade/credentials.json), environment variables (ADE_ENV), and
literal values (priority) in backticks wherever they appear in prose.
Why: the hosted docs generate the CLI reference from help --json and
render a bare --flag as an em dash plus the flag name; agents need
unambiguous literal boundaries; and terminal output prints backticks
literally, which is already this CLI's voice.
tests/test_help_style.py enforces the flag and environment-variable
rules across the help surface's prose fields. Write env vars as a
backticked bare name (ADE_ENV, not $ADE_ENV). Pre-formatted blocks
are exempt: topic bodies and usage lines are terminal layouts and
copy-pasteable commands, so leave them bare.
Relationship to the docs repo
The docs repo (landing-ai/docs) has stricter rules for hosted pages. This file governs text that lives in this repo; the docs repo's generator is the compatibility layer between the two.
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 · 42 lines · 0 tokens per session scan A a0ce09c3f494
writing-style is an agent published in the GitHub repository landing-ai/ade-cli (2,410 stars, last pushed 15d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 407 tokens. 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 agents, from other repositories
wiki-critic
Adversarial reviewer. Finds holes, overclaims, unjustified assumptions, and missing counter-evidence in compiled wiki content. Replaces the Codex CLI "挑漏洞·找反例" role.
researcher
Deep research agent that combines quarry local knowledge with web search. Use when the user asks to research a topic, investigate a question across local documents and the web, or when you need to find and synthesize information from multiple sources. Searches quarry first (local, fast, curated), then web for gaps.…
wiki-cartographer
High-altitude field synthesizer. Reads the compiled wiki/papers, wiki/concepts, and wiki/gaps trees and writes incremental updates to the field/ artifacts — shared assumptions, cross-paper tensions, topic saturation, and the problems.md candidate list — never touching ideas or novelty.
adapter-contract
任何本地 Agent（Hermes / OpenClaw / WorkBuddy / Claude Code / Codex / 任意通用 Agent） 接入本仓库，只需满足下表能力。视觉能力是可选的：没有视觉的 Agent 也能跑完整流程， 由 douyinagentkit.config.yaml 的 vision.ocrprovider / vision.fallbackocr 决定降级方案。.
generic-agent
适用于任意本地 Agent，包括 Claude Code / Codex / 其他 CLI 编码 Agent。 通用能力契约见 adapter-contract.md。.
hermes
本文件说明 Hermes 如何接入 douyin-agent-kit。通用能力契约见 adapter-contract.md；本文只写 Hermes 的具体做法。.