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 skills add paigy-ai/mcp --skill paigygit clone --depth 1 https://github.com/paigy-ai/mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/paigy-ai/mcp/paigy)<a href="https://agentmods.dev/skills/paigy-ai/mcp/paigy"><img src="https://agentmods.dev/badge/skills/paigy-ai/mcp/paigy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paigy-ai/mcp/paigy"><img src="https://agentmods.dev/badge/skills/paigy-ai/mcp/paigy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00024 | $0.00568 |
| Opus 5 | $0.00012 | $0.00284 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
paigy 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 4d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paigy in Codex
Use the Paigy MCP tools supplied by this plugin. Do not invoke a Paigy server from a repository checkout or call the Paigy API directly: the plugin-managed MCP is the source of truth for this Codex identity.
Pairing
- If Paigy says it is unpaired, call its
pairtool and show the returned approval link/code to the user. - Treat pairing and unpairing as explicit user-authorized actions.
- This plugin identifies the client as
codex; do not reuse another client identity such asantigravity.
Sending attention
- Use
contact— the one tool for reaching the user, whether you're telling them something or need an answer. (If your session still showsnotify_userinstead, the MCP hasn't refreshed yet — same fields, use it the same way.) - Two fields:
ask— plain prose, what you need to tell the user or find out from them — andwaiting— what happens to your work meanwhile:"none": you're just informing them."soft": you'd like an answer but can keep working."hard": you are STOPPED until they answer. This reaches them urgently and escalates to a real phone call if unanswered.
- If the user asks you to call them, send
waiting: "hard"and say so in the ask (e.g. "You asked me to call: …"). - Paigy's broker picks the channel, phrasing, and answer format — that is its job, not yours. Keep the ask brief and natural to hear aloud; it may be spoken.
- Use the returned
threadIdfor follow-ups about the same matter. A follow-up on an existing thread supersedes its pending items; use separate threads for independent work.
Replies and callbacks
- A
contactthat rings holds its first ~45 s window itself and returns the outcome inwait; keep waiting on that call withcontact({ wait: notificationId })alone (nothing is sent). A message delivery is never polled for. Usecheck_replieswhen resuming work or checking outstanding items. - A
schedule_callbackrecords an obligation; it does not itself send a notification. When the callback is due, usecheck_replies, then send the promised follow-up on the samethreadId. - Honor the user's requested channel and timing. If a scheduled time has passed, report that clearly and ask before sending a late call unless the user explicitly asked for it to be sent even if late.
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.
- 4d ago Changed 15793398e666
- 10d ago First seen · 32 lines · 24 tokens per session scan A 6f7ef4366135
paigy is a skill published in the GitHub repository paigy-ai/mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 568 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…