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/microdotdo/micro-mcp/micro-sitesnpx skills add microdotdo/micro-mcp --skill micro-sitesgit clone --depth 1 https://github.com/microdotdo/micro-mcpWhat 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 | $0.00140 | $0.01587 |
| Opus 5 | $0.00070 | $0.00794 |
| Sonnet 5 | $0.00028 | $0.00317 |
| Haiku 4.5 | $0.00014 | $0.00159 |
Grade A, and why
micro-sites 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Micro Sites
Turn a focused site idea into reviewed source and a verified live Micro. Keep generation in the current coding harness; Micro supplies the bounded Wasm runtime and trusted hosted capabilities.
Load only the relevant references
- Read project-layout.md before creating or restructuring source.
- Read server-toolchains.md before selecting or changing a server language or build pipeline.
- Read gallery-and-remix.md before selecting or remixing a curated starting point.
- Read browser-sdk.md for browser auth, data, checkout, invocation, or downloads.
- Read server-sdk.md for Abla handlers, SSR, request context, data, purchases, or events.
- Read products-and-files.md before editing
micro.yamlor handling digital files. - Read cli-workflow.md for local build, preview, deploy, or secure account handoff.
- Read project-operation.md for teams, invitations, private sites, custom domains, plans, usage caps, or platform billing.
- Read schedules.md before adding recurring or manually triggered background work.
- Read outbound-email.md before adding receipts, confirmations, or user notifications.
- Read platform-status.md when a live failure may be platform-wide.
- Read deployment-and-maintenance.md for updates, logs, usage, conflicts, GitHub automation, or rollback.
- Read security-and-quality.md before implementing auth, money, data, files, or production changes.
- Read mcp-tools.md before invoking Micro MCP tools.
- Read example-workflow.md for the complete digital-product sequence.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 184 B
- references/browser-sdk.md 2.4 KB
- references/cli-workflow.md 2.0 KB
- references/deployment-and-maintenance.md 5.5 KB
- references/example-workflow.md 1.8 KB
- references/gallery-and-remix.md 1.5 KB
- references/mcp-tools.md 10 KB
- references/outbound-email.md 1.7 KB
- references/platform-status.md 1.3 KB
- references/products-and-files.md 1.7 KB
- references/project-layout.md 1.9 KB
- references/project-operation.md 3.3 KB
- references/schedules.md 1.9 KB
- references/security-and-quality.md 1.7 KB
- references/server-sdk.md 2.9 KB
- references/server-toolchains.md 2.3 KB
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 · 67 lines · 140 tokens per session scan A a86f7faf29a7
micro-sites is a skill published in the GitHub repository microdotdo/micro-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 140 tokens to every session and 1,587 once invoked, about $0.0007 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
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
doca-compress
Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate, decompress-lz4-stream, or decompress-lz4-block tasks on a docacompress context (the hardware supports DEFLATE both directions plus LZ4 decompress; LZ4 encode is NOT…