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/juxt/claude-plugins/tend-docsnpx skills add juxt/claude-plugins --skill tend-docsgit clone --depth 1 https://github.com/juxt/claude-pluginsWhat 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 | $0.00081 | $0.01466 |
| Opus 5 | $0.00041 | $0.00733 |
| Sonnet 5 | $0.00016 | $0.00293 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
tend-docs 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 2d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tend — Technical Documentation
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
Write or update a docs page for a technical audience — developers, operators, integrators. This skill MUST decline, politely, if asked to write for a non-technical audience — marketing copy, end-user help aimed at non-technical readers, general-audience prose. Suggest a different approach instead.
Your Responsibilities
-
Name the audience.
The audience MUST be named — to the user, or in a code comment on the draft — before the page is written.
Technical is not specific enough — pick one:
- Newcomer — has never used this product. Needs just enough context to evaluate or get started. Will re-read.
- Returning power-user Has used it before, coming back for a specific detail. Skims, looks up, leaves. Values terseness.
- Operator mid-task Is running this thing in production and needs to make it do a thing now. Values step-order and concrete identifiers.
- Developer integrating Is wiring this into their own code. Values signatures, examples, failure modes.
If you can't tell from the page's location and surrounding pages, ask.
-
Identify the Diataxis quadrant(s).
Diataxis names four: tutorial, how-to, reference, explanation. Load
chalk:voice'sreferences/docs-quadrants.md— it carries the voice for the three that nothing else here needs.Each section MUST commit to one quadrant, and sections MUST NOT blur. A how-to section that drifts into explanation loses the reader mid-task; an explanation section that drifts into reference buries the mental model.
The test isn't "where does this page live?" — it's "what is this paragraph or section for?". Decide the quadrant of the page as a whole, and of each section, before writing.
-
Discover project conventions.
Read the repo before writing.
In order of priority:
- A docs README (e.g.
docs/README.md) — if present, it's the authoritative style guide. Follow it even where it disagrees with your defaults. - A
CLAUDE.mdat the repo root or in the docs directory. - Existing sibling pages — match their shape (frontmatter, heading depth, changelog format, version-marker style, callout syntax, cross-link style).
- Recent commits and PRs touching docs — they show what's been landing.
- A docs README (e.g.
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.
- 2d ago First seen · 132 lines · 81 tokens per session scan A 05e151334dc4
tend-docs is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 1,466 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 2026-08-31.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.