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/silence-view/llm-language/updatenpx skills add Silence-view/llm-language --skill updategit clone --depth 1 https://github.com/Silence-view/llm-languageWrote 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/silence-view/llm-language/update)<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>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 | $0.00282 | $0.05889 |
| Opus 5 | $0.00141 | $0.02944 |
| Sonnet 5 | $0.00056 | $0.01178 |
| Haiku 4.5 | $0.00028 | $0.00589 |
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.
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)
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.
- 3d ago First seen · 379 lines · 282 tokens per session scan A 4fa1fd72f88e
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.
Other skills, from other repositories
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.