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 flanliulf/SpecLite --skill speclite-distillatorgit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote 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/flanliulf/speclite/speclite-distillator)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-distillator"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-distillator/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/flanliulf/speclite/speclite-distillator"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-distillator.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 | $0.00077 | $0.00749 |
| Opus 5 | $0.00039 | $0.00375 |
| Sonnet 5 | $0.00015 | $0.00150 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
speclite-distillator 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 10d 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
[技能说明] Speclite Distillator 将一组源文档转换为面向 LLM 消费的无损压缩 distillate。它是压缩任务，不是摘要任务；必须保留事实、决策、约束和关系，同时去除人类阅读所需但 LLM 不需要的冗余。
[核心能力]
- 输入分析：运行 scripts/analyze_sources.py 估算 token、识别文件组和路由模式。
- 压缩执行：使用 references/agents/distillate-compressor.md 指令进行 single 或 fan-out 压缩。
- 语义拆分：依据 references/resources/splitting-strategy.md 输出单文件或多 section distillate。
- 格式约束：按 references/resources/distillate-format-reference.md 生成 bullets-only、主题清晰、无重复的结构。
- 完整性检查：用 compressor 返回的 headings 和 named entities 检查遗漏，最多执行 2 次 targeted fix pass。
- 回环验证：在 --validate 模式下使用 references/agents/round-trip-reconstructor.md 进行重建验证。
[执行流程]
1. 校验输入：source_documents 必填，downstream_consumer、token_budget、output_path、--validate 可选。
2. 运行 python3 {skill-root}/scripts/analyze_sources.py --help，再用源路径执行分析，获得 routing、groups 和 token 估算。
3. routing 为 single 时，用 references/agents/distillate-compressor.md 对全部源文件压缩。
4. routing 为 fan-out 时，每组分别压缩，再用同一 compressor 指令合并 intermediate distillates。
5. 对输出执行完整性检查和格式检查，必要时定向修补，最多 2 次。
6. 根据 token_budget 和实际大小决定单文件或 {base-name}-distillate/ 多文件输出。
7. 再次运行分析脚本测量最终 distillate token，返回结构化 JSON 结果。
8. 如传入 --validate，按 round-trip reconstruction 规则生成 validation report。
[注意事项]
- 不得把 distillation 当摘要；摘要丢信息，distillate 必须无损压缩。
- Stage 1 正常情况下不要直接读取源文档，应先使用分析脚本决定路由。
- 若无法 spawn subagent，可读取对应 references/agents/*.md 后在当前上下文按同一规则执行。
- 输出文件必须写到用户指定路径或源文件相邻位置，不得写入项目根目录。
- 当前运行规约不得依赖旧 runtime 路径。
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 486 B
- references/agents/distillate-compressor.md 4.8 KB
- references/agents/round-trip-reconstructor.md 2.7 KB
- references/resources/compression-rules.md 2.6 KB
- references/resources/distillate-format-reference.md 1.7 KB
- references/resources/splitting-strategy.md 3.3 KB
- scripts/analyze_sources.py 9.7 KB runs code
- scripts/tests/test_analyze_sources.py 7.5 KB runs code
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.
- 10d ago First seen · 39 lines · 77 tokens per session scan A 44af5b7d1e71
speclite-distillator is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 749 once invoked, about $0.0004 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
doc-drift
Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory…
EU AI Act Documentation
What compliance documentation to produce under the EU AI Act — Annex IV technical documentation, EU declaration of conformity, risk-management file, data-governance records, and GPAI training-data summary — and how to structure it.
Memory System
Maintain a tiered, file-based memory system so project context and decisions survive across sessions instead of being rediscovered or contradicted each time.
context-handoff
Write a structured handoff file (YAML frontmatter + prose) to docs/superpowers/handoff.md before /clear or /compact. Different from /context-save (gstack) — survives across machines and restores without gstack installed.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.