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/lync-cyber/cataforge/platform-auditnpx skills add lync-cyber/CataForge --skill platform-auditgit clone --depth 1 https://github.com/lync-cyber/CataForgeWrote 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/lync-cyber/cataforge/platform-audit)<a href="https://agentmods.dev/skills/lync-cyber/cataforge/platform-audit"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/platform-audit.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 | $0.00152 | $0.04379 |
| Opus 5 | $0.00076 | $0.02190 |
| Sonnet 5 | $0.00030 | $0.00876 |
| Haiku 4.5 | $0.00015 | $0.00438 |
Grade A, and why
platform-audit 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 6d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
平台能力审计 (platform-audit)
能力边界
- 能做: 检索各 AI IDE 最新能力文档、与现有 profile.yaml 差异分析、更新配置/源码/测试、运行合规检查
- 不做: 新增全新平台 adapter（需先在
src/cataforge/adapter/platform/创建 adapter 类）、修改核心调度逻辑、审查.cataforge/下框架内部 agents/skills/hooks（由 framework-review 负责）
设计原理
CataForge 通过多层抽象覆盖 AI IDE 的能力差异:
- 核心能力 ID (
CAPABILITY_IDS) — 工具级映射（file_read, shell_exec, agent_dispatch 等；其中OPTIONAL_CAPABILITY_IDS所列项可选） - 扩展能力 ID (
EXTENDED_CAPABILITY_IDS) — 部分平台独有的工具（notebook_edit, browser_preview, image_input, code_review） - Agent 配置 (
AGENT_FRONTMATTER_FIELDS) — agent 定义 frontmatter 字段的跨平台超集 - 平台特性 (
PLATFORM_FEATURES) — boolean 功能标志（cloud_agents, agent_teams, scheduled_tasks 等；清单与计数以types.py为准） - 权限模型 — 审批模式集，各平台在
profile.yaml的permissions.modes声明所支持的子集 - 模型路由 — 可用模型列表和 per-agent 模型选择支持
- Hook 事件 — 5 个标准事件 + 降级策略
每个平台通过 profile.yaml 声明它如何映射这些抽象。平台版本快速迭代，工具名称/hook 事件/agent 格式/功能特性随时可能变化（各平台当前能力快照见 references/capability-matrix.md）。本 skill 将"检索 → 对比 → 更新 → 验证"的完整审计流程标准化，防止配置漂移。
输入规范
调用方提供:
- 审计范围: 平台 ID 列表（默认 all = claude-code, cursor, codex, opencode）
- 关注维度: tools / hooks / dispatch / agent / features / permissions / models / mcp（默认全部）
- 触发原因（可选）: 如"Cursor 刚发布 v3.2"或"Codex 新增了沙箱模式"
输出规范
- 差异分析报告（结构化 Markdown）
- 更新后的
profile.yaml文件 - 必要时更新的源码文件（adapter / bridge / types / conformance）
- 更新后的测试文件
- 合规检查（含扩展合规）+ 测试套件通过确认
操作指令
| 模式 | 适用场景 | 详见 |
|---|---|---|
| full | 定期对齐（建议每月一次）或已知某平台有重大版本更新 | 指令 1 |
| quick-check | 只想知道当前配置是否过期，不执行修改 | 指令 2 |
deep <platform_id> |
某平台刚发布重大更新，需深度审计 | 指令 3 |
evaluate <platform_name> |
评估新 AI IDE 是否可接入（不修改仓库内任何文件，输出可行性报告供决策） | references/evaluate-new-platform.md |
| offline | CI / 本地静态门禁：不联网、不需 LLM，只跑可执行的合规子集 | 指令 4 |
指令1: 完整审计 (full)
Phase 1: 文档检索与情报收集
此阶段的目标是建立每个平台的最新能力快照。不要依赖训练数据——平台更新非常频繁，profile.yaml 可能已经过期数月。
Step 1: 读取当前配置基线
并行读取所有目标平台的 profile.yaml (.cataforge/platforms/<platform_id>/profile.yaml)，提取并记录每个平台当前的:
What ships with it
6 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.
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.
- 6d ago First seen · 276 lines · 152 tokens per session scan A ecd35a892583
platform-audit is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 4,379 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…