update

update is a skill for Claude Code, Codex from Silence-view/llm-language. It costs 282 tokens per session (5,889 once invoked), scanned A, original, MIT.

A research routine for tracking changes in Claude Code, its models, prompting methods, memory features, and recommended practices. It searches official documentation and other published sources.

In plain words
What is it for?
Use it to review recent Claude Code developments, check whether model names or features have changed, and update project guidance accordingly.
Why use it?
It helps you notice model retirements, new settings, billing changes, and other updates that could make existing workflows outdated.

Skill for Claude CodeCodex

Part of the llm-language plugin — 4 skills, 5 hooks shipped together

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/silence-view/llm-language/update
Any agent
npx skills add Silence-view/llm-language --skill update
Clone the repo
git clone --depth 1 https://github.com/Silence-view/llm-language

Made for: Claude Code, Codex.

Or install llm-language, the plugin that ships this one along with the rest of its 4 skills, 5 hooks.

Wrote 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.

agentmods badge for update

README.md
[![agentmods](https://agentmods.dev/badge/skills/silence-view/llm-language/update.svg)](https://agentmods.dev/skills/silence-view/llm-language/update)
Your own site
<a href="https://agentmods.dev/skills/silence-view/llm-language/update"><img src="https://agentmods.dev/badge/skills/silence-view/llm-language/update.svg" alt="Measured on agentmods" height="20"></a>
Per session 282 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,889 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 $0.00282 $0.05889
Opus 5 $0.00141 $0.02944
Sonnet 5 $0.00056 $0.01178
Haiku 4.5 $0.00028 $0.00589

Measured 3d ago against content hash 4fa1fd72f88e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update 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 3d 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.

skills/update/SKILL.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llm-language:update — Self-Evolution Research Agent (v3.2)

v3.2 era note (2026-06-11)

The frontier moved: Claude Fable 5 (claude-fable-5, Mythos-class tier ABOVE Opus, GA 2026-06-09) and Opus 4.8 (claude-opus-4-8, new workhorse default since 2026-05-28). Terminology: "Mythos-class", NEVER "Claude 5 family" (docs never use it). Authoritative era reference: skills/llm-language/references/fable-5-era.md. New monitored surfaces: refusal API (stop_reason: "refusal" + stop_details.category), fallbacks beta param, classifier rerouting to Opus 4.8 (<5% sessions) + silent degradation controversy, dynamic workflows / ultracode, nested sub-agents (≤5 levels), advisor tool (beta), AutoDream (unofficial idle memory consolidation), MessageDisplay + post-session hooks.

P0 deprecation table (refresh each run): Sonnet 4 + Opus 4 retire 2026-06-15 (→ claude-sonnet-4-6 / → claude-opus-4-8); Agent SDK billing split 2026-06-15 (separate monthly credit pool, one-time manual claim required); Fable 5 leaves plan limits 2026-06-22→23 (prepaid usage credits); claude-mythos-preview retires 2026-06-30 (→ claude-mythos-5); fast mode on Opus 4.6 removed ~late June; Opus 4.1 retires 2026-08-05 (→ claude-opus-4-8).

Overview

Autonomous research agent that keeps llm-language current by searching for:

  • Claude model updates (Fable 5 / Mythos-class, Opus 4.8+, Sonnet 4.6+, Haiku 4.5+, new effort tiers, adaptive thinking, task budgets, tokenizer changes, refusal/fallback API surface)
  • Claude Code features (hooks, skills, plugins, memory, output styles, agent view, background sessions, /goal + Outcomes pattern)
  • Long-horizon autonomy primitives (/goal, Outcomes, Dreaming, separate-evaluator patterns)
  • New prompting research (arXiv, NeurIPS, ICLR, ACL, EMNLP — 2025-2026; MAD, MASPO, Tournament-of-Prompts, OPTAGENT, SDRL, Agentic Memory)
  • Memory systems (auto-memory MEMORY.md, Memory Tool API, Memory Import, claude-mem, mem0/letta/zep/cognee, Dreaming consolidation)
  • Agent framework ecosystem (OpenAI Agents SDK, Google ADK + A2A 1.2, Microsoft Agent Framework, CrewAI, LangGraph)
  • Community innovations (plugins, skills, hooks, marketplace, awesome-claude-code-toolkit, claude-mem)
  • YouTube content (demos, reviews, walkthroughs — via yt-learner skill)
  • Deprecation & billing watch (P0: Sonnet 4 / Opus 4 retire 2026-06-15; Agent SDK Credit pool split)

Read the full file on GitHub · 379 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. 3d ago First seen · 379 lines · 282 tokens per session scan A 4fa1fd72f88e

Subscribe to this mod's changes

update is a skill published in the GitHub repository Silence-view/llm-language (2 stars, last pushed 2mo ago), licensed MIT. It adds 282 tokens to every session and 5,889 once invoked, about $0.0014 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.