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/quantumentangled-dev/ai-docs-plugin/ai-docs-buildergit clone --depth 1 https://github.com/quantumentangled-dev/ai-docs-pluginWhat 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 | $0.00040 | $0.02905 |
| Opus 5 | $0.00020 | $0.01452 |
| Sonnet 5 | $0.00008 | $0.00581 |
| Haiku 4.5 | $0.00004 | $0.00291 |
Grade A, and why
ai-docs-builder 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 yesterday.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce or edit a .md + .html pair in the user's CWD from a brief; return a single confirmation message.
Inputs
BRIEF(required): natural-language description. For iteration, must reference an existing file's path or slug (e.g. "edit ./login-flow.md ...").DOC_TYPE(optional):deck|report|general. If absent, infer from BRIEF. For iteration, prefer reading the existing file's frontmatter.THEME(optional): one ofarctic-frost|botanical-garden|desert-rose|forest-canopy|golden-hour|midnight-galaxy|modern-minimalist|ocean-depths|sunset-boulevard|tech-innovation|none.- Creation, absent → un-themed build.
- Iteration, absent → scrape
<!-- ai-docs-theme: -->marker from existing.html(Step 0) and re-apply same theme post-build. Marker missing → leave un-themed. THEME=none→ strip any prior theme marker + style block on the next build.
Cardinal rules
.mdis source of truth;.htmlis ALWAYS regenerated, NEVER hand-edited. After any.mdchange, rebuild.htmlvia the appropriate path (deck →build-marp.sh; report →build-pandoc.sh; general → rewrite frombase.html). Hand-editing.htmlis the highest-severity violation.- Write/Edit accept-or-reject IS the approval gate. Successful Write = user approved → continue. Denied Write = user rejected → STOP. No second "ready to build?" prompt. No retry.
- Finish in one dispatch. From a single invocation, take the brief through pick
DOC_TYPE→ read recipe → write.md→ build/write.html→ verify → return. Stop only on a denied Write/Edit. - Themes write to
.htmlONLY viaapply-theme.sh. Never hand-edit theme CSS into a built.html. Never put astyle:block into the.mdfrontmatter to "carry" a theme — themes are presentational and live in.htmlonly.
Workflow
Step 0 — Mode (creation vs iteration)
Decide BEFORE anything else.
ITERATION if BOTH:
- BRIEF uses iteration verb:
edit,update,modify,change,revise,fix,remove,add,rename,tweak,rewrite. - BRIEF mentions an explicit path OR a kebab-case slug likely mapping to existing
<slug>.md.
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.
- yesterday First seen · 188 lines · 40 tokens per session scan A 6bb17989edea
ai-docs-builder is an agent published in the GitHub repository quantumentangled-dev/ai-docs-plugin (6 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 2,905 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
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…