hello-aigent

A set of instructions for following Hello Aigent feeds, which are opt-in signed update streams that websites can publish for AI agents. It covers checking for feeds, subscribing, retrieving and verifying updates, listing subscriptions, and unsubscribing.

In plain words
What is it for?
Use it to check whether a website has a feed, subscribe or unsubscribe, retrieve new updates, verify their signatures, and create digests.
Why use it?
It gives the agent a defined way to receive website updates while requiring consent before following a feed and verification before acting on one.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/helloaigent-dev/helloaigent-subscriber/hello-aigent
Any agent
npx skills add helloaigent-dev/helloaigent-subscriber --skill hello-aigent
Clone the repo
git clone --depth 1 https://github.com/helloaigent-dev/helloaigent-subscriber

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00104 $0.01183
Opus 5 $0.00052 $0.00592
Sonnet 5 $0.00021 $0.00237
Haiku 4.5 $0.00010 $0.00118

Measured yesterday against content hash 05532983262a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hello-aigent 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.

skills/hello-aigent/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hello Aigent subscriber

Hello Aigent is an opt-in subscribe layer for AI agents (RSS-for-agents). A website can publish a signed feed. An agent may subscribe, fetch new updates, verify the Ed25519 signature, and only then act.

This plugin talks to the existing Hello Aigent subscriber MCP (@helloaigent-dev/subscriber). There is no API key. Subscriptions, tokens, and policy live locally under ~/.hello-aigent/ (never show stored tokens).

Many people using this plugin are not developers. Speak plainly. Confirm what you are about to do before you subscribe.

When to use this skill

  • The user asks to subscribe their agent to a site or to Hello Aigent.
  • The user asks whether a website has a Hello Aigent feed.
  • The user wants new updates, a digest, or to stop following a feed.
  • You are about to use any hello_aigent_* tool.

Subscribe only with the principal's consent — the person (or account) this agent acts for.

  • If they said to subscribe to a named site or feed, that is consent for that feed.
  • If you merely found a feed while visiting a site, tell them and ask before calling hello_aigent_subscribe.
  • Do not silently auto-subscribe in chat just because a site has a feed. hello_aigent_check_site may subscribe on its own when local policy is auto_subscribe: on. Prefer hello_aigent_check_site only to detect a feed, then subscribe explicitly after they agree — or ask them to set policy if they want automatic subscribe-on-visit.
  • Unsubscribe is always allowed and is one call. Offer it if they change their mind.

The default principal is a local user@host identity until they set a stable one (often an email) in ~/.hello-aigent/policy.json.

How to find a feed

Publishers advertise discovery at:

https://<site>/.well-known/hello-aigent.json

Example (live dogfood feed): https://helloaigent.devhttps://helloaigent.dev/.well-known/hello-aigent.json

If the user names a website, check that discovery URL (or pass any page URL on the site to hello_aigent_check_site). If there is no discovery file and no rel="agent-feed" link, say the site does not publish a Hello Aigent feed yet.

Read the full file on GitHub · 91 lines

Changes

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.

  1. yesterday First seen · 91 lines · 104 tokens per session scan A 05532983262a

Subscribe to this mod's changes

hello-aigent is a skill published in the GitHub repository helloaigent-dev/helloaigent-subscriber (0 stars, last pushed 6d ago), licensed MIT. It adds 104 tokens to every session and 1,183 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens