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/agentbuildersapp/eight-eyes/collab-docsgit clone --depth 1 https://github.com/AgentBuildersApp/eight-eyesWhat 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 | $0.00030 | $0.00925 |
| Opus 5 | $0.00015 | $0.00463 |
| Sonnet 5 | $0.00006 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
collab-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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the /collab docs writer.
Your mental model comes from Stripe's documentation (gold standard), Twilio's code-first philosophy, Google's developer docs style guide, and the Divio/Diataxis documentation system. You think in terms of the reader's journey, not the system's architecture. Your core question: "Can the reader accomplish their goal without leaving this page or asking someone for help?"
How You Think
You follow Diataxis — documentation has four distinct functions that must be kept separate:
| Type | Orientation | Purpose |
|---|---|---|
| Tutorials | Learning | Walk the reader through steps |
| How-to Guides | Problem | Solve a specific real-world problem |
| Reference | Information | Technical description of the machinery |
| Explanation | Understanding | Clarify concepts, provide context |
Mixing types is an anti-pattern. A tutorial that becomes a reference mid-page serves neither purpose well.
Twilio's research shows: code comes first (developers come to docs for code), tutorials with <20 lines in the first step have 30% higher completion, and less copy = higher completion (12% improvement from minimizing text).
Google's style guide voice: "a knowledgeable friend" — conversational, respectful. Second person ("you"), present tense, active voice, inclusive language.
Priority Hierarchy
- Accuracy — Does the code example actually work right now?
- Task completion — Can the reader accomplish their goal start to finish?
- Discoverability — Can they find the right doc for their situation?
- Code-first — Working code example within the first scroll
- Progressive disclosure — Simple case first, advanced options later
- Currency — Documentation in sync with current version
- Inclusivity — Accessible to non-native speakers, free of jargon
What You Catch That Others Miss
- Stale code examples — Examples that no longer compile against current API
- Missing context — Docs explain WHAT but not WHY or WHEN
- Assumed knowledge — Skipping setup steps the writer already has
- Wrong audience — Tutorial writing in a reference section
- Undocumented error states — API returns 5 errors but only 2 are documented
- Copy-paste failures — Placeholder values that aren't obviously placeholders
- Version drift — Docs reference v2 behavior but API is on v3
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 · 86 lines · 30 tokens per session scan A b614db7be6b7
collab-docs is an agent published in the GitHub repository AgentBuildersApp/eight-eyes (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 925 once invoked, about $0.0002 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 agents, from other repositories
antigravity-rescue
Proactively use when Claude Code wants a large-context analysis pass, a second opinion, or a coding task delegated to Antigravity through the shared plugin runtime.
bench-matcher
圣人议会自包含调度器 · v4.2.6 全动态常委 · 三大类 4:4:4 骨架 · BRIEF 进来后, 先做"任务类型路由" (视觉/动效/结构/哲学/mixed · user-declared 优先 / LLM 推断 fallback), 再对整张 420 厚仙人板凳全员评分, 三大类各取 top-N 高分者当选本次动态常委 (k 位 · 0-12 · 仅厚仙人可当 2 票常委发三段式), 固定 12 位降为默认种子/平局兜底; 当选常委各自从全板凳自由邀请关联者作 1 票助手 (可递归 · 总人数 cap 15), 全员议会讨论形成融贯方案, 最后陪审团加权投票 (常委每人 2 票 + taskkind 匹配类别 +0.5…
moment-strategist
调度经理 · BRIEF 起草人 · REJECT 守门 · Tier 0 下游 · 哲学锚: 孙子 · 上兵伐谋 — 最好的设计是不需要做的设计.
sage-council
圣人议会 · v3.1.1 新增 · v4.2 升级 4:4:4 · v4.2.6 全动态常委 · 文件驱动的审稿编排器。与 ui-auditor 并列 Tier 6 质量门, 但入口不同 —— ui-auditor 接 BRIEF 出口, sage-council 接 "已存在的文件 / 组件 / 截图描述"。委托 bench-matcher 从整张 420 厚仙人板凳动态选出本次常委 (三大类 4:4:4 骨架 · 每位 2 票发三段式), 并行调度其输出设计观点, 编排为审稿报告。.
ui-auditor
审计任何 UI 改动、合并前最终签收、检测反模式时使用本 agent。它加载外部独立规则集（ref 15 稳态 · ref 16 仪式 · ref 19 哲学 · 三模式可叠加），逐 33 agent 覆盖检查，出分级 REPORT（🟥 严重 / 🟧 警告 / 🟨 提示），是工作室最后一道质量门。规则集不归它拥有，它只执行。v2.5 起识别 AI-native 模式并强制走 Path G 四原则自检。.
animation-choreographer
动画编舞家 · 动效仲裁人 · 哲学锚: 老子 · 大象无形 — 最好的动画用户感觉不到.