ai_pulse

A reading assistant that gathers current AI news, model releases, GitHub projects, and research highlights into briefings and a reading list.

In plain words
What is it for?
Getting AI briefings, finding topic-specific updates and repositories, and saving or managing reading-list items.
Why use it?
It reduces the work of tracking fast-changing AI developments across different sources.

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/proxy2021/enso/ai_pulse
Any agent
npx skills add Proxy2021/Enso --skill ai_pulse
Clone the repo
git clone --depth 1 https://github.com/Proxy2021/Enso

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 299 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 $0.00024 $0.00299
Opus 5 $0.00012 $0.00150
Sonnet 5 $0.00005 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash f64044485fbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai_pulse 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.

server/skills/ai_pulse/SKILL.md · 43 lines

What it actually says

Ai Pulse

Stay current on AI developments with trending news, GitHub repos, and research highlights with a reading list

Available Tools

enso_ai_pulse_briefing (primary)

Get a daily AI briefing with the latest news, model releases, and trending topics

Parameters:

  • topic (string): Optional focus topic (e.g. 'LLMs', 'computer vision', 'robotics')

enso_ai_pulse_trending_repos

Discover trending AI/ML GitHub repositories

Parameters:

  • category (string): Category filter: all, llm, vision, agents, tools, datasets (default: all)

enso_ai_pulse_search_topic

Search for a specific AI topic, tool, paper, or technology

Parameters:

  • query (string): Search query about AI topics

enso_ai_pulse_reading_list

Manage your AI reading list — save, view, or remove items

Parameters:

  • action (string): Action: view, save, remove
  • title (string): Title of item to save
  • url (string): URL of item to save
  • summary (string): Summary of item to save
  • itemId (string): ID of item to remove
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. 2d ago First seen · 43 lines · 24 tokens per session scan A f64044485fbf

Subscribe to this mod's changes

ai_pulse is a skill published in the GitHub repository Proxy2021/Enso (5 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 299 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.

Related

Other skills, from other repositories