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 commands/hjxccc/silk-starry/silkgit clone --depth 1 https://github.com/hjxccc/silk-starryWrote 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/commands/hjxccc/silk-starry/silk)<a href="https://agentmods.dev/commands/hjxccc/silk-starry/silk"><img src="https://agentmods.dev/badge/commands/hjxccc/silk-starry/silk.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 5.1 | $0.00031 | $0.00188 |
| Opus 5 | $0.00015 | $0.00094 |
| Sonnet 5 | $0.00006 | $0.00038 |
| Haiku 4.5 | $0.00003 | $0.00019 |
Grade A, and why
silk 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 5d 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.
What it actually says
使用 silk-starry skill 处理下面这件事——它会自己判断该走哪个动作（生成 / 体检精简 / 进化升级 / 全仓盘点 / 多文件编排 / 记忆体检），无需我指定：
$ARGUMENTS
若上面为空，就先盘点当前项目的 CLAUDE.md/AGENTS.md 现状，并问我想做什么。 所有会写文件/删记忆的动作，先给我看 diff、等我确认。
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.
- 5d ago First seen · 12 lines · 31 tokens per session scan A a19f3872e4fd
silk is a command published in the GitHub repository hjxccc/silk-starry (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 188 once invoked, about $0.0002 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 commands, from other repositories
check
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.
iai-directive
Record a standing order the user typed themselves, as an explicit memory directive.
encode-repo
Bootstrap a repository into Forgetful's knowledge base.
memory-list
List recent memories from Forgetful.
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
vitaecontext-vitaegraph
Create, validate, index, or use a private VitaeGraph.