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/evoclaw/amplify/method-framework-designnpx skills add EvoClaw/amplify --skill method-framework-designgit clone --depth 1 https://github.com/EvoClaw/amplifyWhat 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 | $0.00045 | $0.07726 |
| Opus 5 | $0.00023 | $0.03863 |
| Sonnet 5 | $0.00009 | $0.01545 |
| Haiku 4.5 | $0.00005 | $0.00773 |
Grade A, and why
method-framework-design 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 2d 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 — 747 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Method & Framework Design (Phase 3)
Overview
This is the most critical branching point in the research workflow. Type M and Type D projects follow completely different design paths. Executing the wrong path — or skipping design entirely — guarantees wasted effort.
On-Demand Literature Search (Active Throughout Phase 3)
- "Has anyone tried approach X for this problem?"
- "What's the current SOTA for sub-task Y?"
- "Is there theoretical justification for design choice Z?"
- "What hyperparameters did paper W use for this baseline?"
When this happens: SEARCH IMMEDIATELY. Do not guess, do not rely on memory, do not defer to "we'll check later." Use web search, arXiv, Google Scholar, or any available tools to find the answer NOW.
Update the literature record: Any new papers found during Phase 3 should be added to docs/02_literature/paper-list.md with a note: [Found during Phase 3 — method design].
If search fails (no results, paywall, or tools unavailable): do NOT fabricate an answer. Instead:
- Note the specific question that needs answering: "Need to know: [question]"
- Record it in the exploration report
- Ask the user: "I couldn't find information on [X]. Do you know, or can you check?"
- Continue with what you know, marking the gap as an assumption to verify
This applies equally to Phase 4, 5, and 6. Literature retrieval is a continuous activity, not a one-time Phase 1 task.
Re-Entry from Phase 4a (Exploratory Return Path)
If the user returns to Phase 3 from Phase 4a exploration (because baseline results or data analysis revealed the method/analysis design needs rethinking), do NOT start from scratch:
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.
- 2d ago First seen · 747 lines · 45 tokens per session scan A b3fbd3add131
method-framework-design is a skill published in the GitHub repository EvoClaw/amplify (12 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 7,726 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 2026-08-30.
Other skills, from other repositories
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
xlsx
当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要：打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件（例如添加列、计算公式、格式化、制图、清理混乱数据）；从头创建新的电子表格或从其他数据源创建；或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及（如"我下载目录里的 xlsx"）——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件（格式错误的行、错位的表头、垃圾数据）清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets…
terraform-cli-setup
Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装，确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置，凭证在实际使用时由 terraform-skill 引导。.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.
winui-ui-testing
Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…