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 instructions/invertase/docs.page/agents-mdgit clone --depth 1 https://github.com/invertase/docs.pageWhat 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 | $0.00666 | $0.00666 |
| Opus 5 | $0.00333 | $0.00333 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
docs.page AGENTS.md 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs.page — agent guidance
This file orients coding agents working in the docs.page monorepo. For human contributors, see CONTRIBUTING.md.
Project overview
docs.page serves markdown documentation from public GitHub repositories as modern,
agent-ready sites (MCP, llms.txt, optional Ask AI). The active codebase is a
Bun workspace centered on a Next.js app and shared packages.
Monorepo layout
app/ Next.js app — rendering, API routes, MCP, agent panel
packages/cli/ @docs.page/cli — init, check, preview
packages/mdx-bundler/ Shared markdown → doc IR pipeline
docs/ Product documentation (MDX)
docs.json Site navigation for this repo's docs
skills/ Agent skills (SKILL.md per skill)
Commands
| Task | Command |
|---|---|
| Install | bun install (repo root) |
| Dev server | bun dev or cd app && bun dev |
| Format + lint | bun run check (Biome, repo root) |
| CLI dev | cd packages/cli && bun run dev |
| CLI typecheck | cd packages/cli && bun run typecheck |
Conventions
- Runtime — Bun for installs and scripts; Next.js App Router in
app/. - Lint/format — Biome (
biome.json). Runbun run checkbefore finishing. - UI — shadcn/ui components live in
app/src/components/ui/. Use existing primitives before adding dependencies. - Next.js — Read
app/AGENTS.mdandnode_modules/next/dist/docs/for Next.js 16 APIs (breaking vs training data). - Shared markdown pipeline — Changes to doc rendering belong in
packages/mdx-bundler/when they affect both app and CLI preview. - Scope — Minimal diffs; match existing patterns; update
docs/for user-visible behavior.
Environment
Local app development against live GitHub content requires GITHUB_PAT in
app/.env.local. GitHub App credentials are only needed for webhook work.
See CONTRIBUTING.md for setup.
Do not commit secrets, .env, or generated artifacts (.next/, dist/).
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 · 66 lines · 666 tokens per session scan A e6224bfc9c48
docs.page AGENTS.md is an instructions file published in the GitHub repository invertase/docs.page (671 stars, last pushed 4d ago), licensed Apache-2.0. It adds 666 tokens to every session, about $0.0033 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 instructions, from other repositories
Skill_Seekers CLAUDE.md
Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).
Skill_Seekers AGENTS.md
Instructions for yusufkaraaslan/Skill_Seekers, covering agents.md - skill seekers, project overview, key capabilities, setup and with dev tools (pytest, ruff, mypy, coverage).
PowerDocu copilot-instructions.md
Instructions for modery/PowerDocu, covering claude.md — powerdocu codebase guide, project overview, repository structure, submodule: powerdocu.common and key contents of powerdocu.common.
pitchdocs CLAUDE.md
Instructions for littlebearapps/pitchdocs, covering pitchdocs, project architecture, conventions, key files and when modifying this plugin.
PowerDocu CLAUDE.md
Instructions for modery/PowerDocu, covering claude.md — powerdocu codebase guide, project overview, repository structure, submodule: powerdocu.common and key contents of powerdocu.common.
pitchdocs AGENTS.md
Instructions for littlebearapps/pitchdocs, covering pitchdocs, documentation standards, available skills, agent pipeline and workflow commands.