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 skills add SuanFishXYY/sptler --skill sptler-litegit clone --depth 1 https://github.com/SuanFishXYY/sptlerWrote 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/suanfishxyy/sptler/sptler-lite)<a href="https://agentmods.dev/skills/suanfishxyy/sptler/sptler-lite"><img src="https://agentmods.dev/badge/skills/suanfishxyy/sptler/sptler-lite/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/suanfishxyy/sptler/sptler-lite"><img src="https://agentmods.dev/badge/skills/suanfishxyy/sptler/sptler-lite.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00160 | $0.02665 |
| Opus 5 | $0.00080 | $0.01333 |
| Sonnet 5 | $0.00032 | $0.00533 |
| Haiku 4.5 | $0.00016 | $0.00266 |
Grade A, and why
sptler-lite 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
算鱼议会 · 精简模式 /sptler-lite
/sptler-lite {问题}=/sptler# {问题}的独立入口——省 token 快车道。
本 skill 是 /sptler 的精简变体,复用 sptler 的 28 圣人 + 22 脚本 + references,只换运行时行为(省 token)。所有脚本在 sptler 目录内运行,--lite flag 强制精简行为。
定位 sptler 目录(跨平台,不硬编码路径):优先 ${CLAUDE_SKILL_DIR}/../sptler(Claude Code 标准);若该变量未替换或不存在,按序检查 ~/.claude/skills/sptler、~/.codex/skills/sptler、.github/skills/sptler、.claude/skills/sptler,取第一个含 scripts/ 的。下文 <SPTLER_DIR> 代指定位到的目录。
触发
/sptler-lite {问题}//sptler# {问题}//议会# {问题}//议一议# {问题}
精简行为(强制)
- 不读 references:orglaw/philosophy/runtime/templates/memory_philosophy 都不开,下面 cheat-sheet 即内核
- verdict 优先、硬上限 ≤3:
cd <SPTLER_DIR> && python scripts/routing/route_sages.py --topic "<问题>" --lite--lite强制:verdict优先、规模封顶3、formal降级fast、专利场景硬拒绝(lite_rejected=true+0人,提示用标准 /sptler)——挖掘例外(D11/D42):feature_analysis:false的挖掘场景 lite 放行(轻量版:无反问/≤3人/仅出权利要求骨架,无说明书);route_sages stderr 提示"要完整草稿请用标准 /sptler";输入过缺→quality_concern+建议标准lite_quality_concern=true→ 邹蕴提示"本题formal级,lite 3人降级可能不充分,建议标准 /sptler"
- 薄灵魂:
python scripts/memory/summon_sage.py --sage <名> --lite(一行:身份+命题+冲突+边界+自警+追问+句式,若有lite记忆加"上次lite"指针) - 议会张力(≤3 人时):
python scripts/routing/tensions.py --roster <名单>——注入入会圣人间的预设张力对(如王升vs张鑫"结构vs控制");若该对有共议历史(RELATIONS.json),张力演化(交锋从"谁先"转"如何协同")。驱动辩论有交锋,且随共议磨合。 - 无记忆注入:lite 跳记忆/关系/历史(无魔法时刻——这是 /sptler-lite 的明确代价)
- 单轮、零 AskUser:4 段裁决(见下)+ 最简结果 md,然后
议会到此结束。
lite 裁决 4 段结构(强制 · 命题必须用上)
lite 不是"3 句话应付",而是用命题推理给可执行判断。主笔圣人 4 段发言:
[主笔] 结论:{一句话判断}——按"{核心命题}",{用命题推导出的理由}。
[主笔] 落地:{2-3 条可执行要点,具体到"写什么/查什么/改什么"}。
[主笔] 风险:{1 句最大风险或前置条件}。
[邹蕴] 收口:{1 句总结}。议会到此结束。
- 结论段必须引用主笔的核心命题推理(不是空泛判断)——如卢若雨裁决边界问题,结论须带"权利要求边界=发明领土"这层思维。
- 落地段的可执行要点由"必须追问"驱动——把圣人的追问(如王升"骨架是什么/边界在哪")转成具体动作("补XX骨架""钉死XX边界"),不是凭空编要点。转化范式:每个追问→1条要点(追问"位置如何定义"→要点"在独权中定义AOA角度估计的位置关系:'基于蓝牙AOA信号'限定信号来源,不限定算法")。要点须直接回答追问,不是绕开。
- 风险段必须对照"失败模式/自警"——圣人自警的盲区(如周全"不同法域差异未对齐")若与本议题相关,须在风险段点出,防圣人执念过度。
- 有"上次lite"指针时,结论段可引用("上次我们议过X→结论Y,这次...")。
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.
- 11d ago First seen · 104 lines · 160 tokens per session scan A f0d838fa8df2
sptler-lite is a skill published in the GitHub repository SuanFishXYY/sptler (2 stars, last pushed 2mo ago), licensed MIT. It adds 160 tokens to every session and 2,665 once invoked, about $0.0008 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
assess-interview-candidate
A structured hiring-assessment workflow that turns a candidate's résumé and a job description into reviewable evidence, interview questions, and an offline HTML report for interviewers.
user-profile-keeper
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…
run-history-skill-upgrader
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…
session-handoff-prompt
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…
task-forest
Maintains a repo-local task forest or task DAG for the current workspace. Use when the user asks to initialize or update a task forest, close a session, summarize evolving project work, align a request with a global goal, track progress/history/deviations/todos, save or apply a task proposal, or export the…
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.