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/framework-updatenpx skills add lync-cyber/CataForge --skill framework-updategit clone --depth 1 https://github.com/lync-cyber/CataForgeWhat 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 | $0.00155 | $0.03002 |
| Opus 5 | $0.00077 | $0.01501 |
| Sonnet 5 | $0.00031 | $0.00600 |
| Haiku 4.5 | $0.00015 | $0.00300 |
Grade A, and why
framework-update 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CataForge 框架同步 (framework-update)
能力边界
- 能做: 包↔scaffold 版本差异检测、pip/uv 包升级、scaffold 增量刷新、IDE 产物部署、doctor 验证、按
references/version-migration.md提示升级区间的更新重点与迁移动作、upgrade.state 簿记、项目 init/resume 分流 - 不做: 修改项目业务代码、升级操作系统依赖、跨平台 adapter 变更(由 platform-audit 负责)、内嵌 Project Bootstrap 协议(仅委托 orchestrator 执行)
输入规范
- 操作指令:
check(只读检测)、apply(同步并初始化/恢复)、verify(迁移检查) - 无参数时默认执行完整流程(check → 确认 → apply)
--dry-run: 仅在 apply 中有效,预览 plan 不写盘--upgrade-package: 在 apply 中强制执行 pip/uv 包升级(缺省仅在 check 探测到包落后时升级)- 本 skill 是脊柱命令
cataforge bootstrap的薄编排层
输出规范
- 版本对比(scaffold 版本 vs 已安装版本)与初始化状态({INSTRUCTION_FILE} 是否存在)
- scaffold 刷新文件统计(写入数 / 保留数)、部署产物清单
- 升级区间的更新重点摘要与迁移动作清单(来自 version-migration 迁移要点)
- 迁移检查结果(PASS / SKIP / FAIL 逐项)
- upgrade.state 更新确认(框架版本字段由 deploy 阶段盖入)
- init/resume 决策与已装配的执行环境命令
操作指令
指令1: 版本与初始化状态检测 (check)
Step 1: 读取当前状态
执行:
cataforge upgrade check
从输出记录 installed_version(Installed package 行)、scaffold_version(Scaffold version 行)、二者是否一致,以及 {INSTRUCTION_FILE} 是否存在(→ 需 init / 已初始化)。
Step 2: 报告
已安装包 : <installed_version>
Scaffold : <scaffold_version>
版本状态 : up-to-date | outdated
项目状态 : 未初始化(无 {INSTRUCTION_FILE}) | 已初始化
outdated 或未初始化时提示用户运行 framework-update apply;outdated 时补一句:升级完成后会按新版迁移要点提示需人工跟进的动作(当前 scaffold 内的 version-migration 仍是旧版内容,升级前不据其预告新版变更)。
指令2: 同步并初始化/恢复 (apply)
单一脊柱
cataforge bootstrap(幂等 setup→upgrade→deploy→doctor)只在 Step 3 调用一次;前置包升级、后置簿记、init/resume 分支分别包裹其前后。
Step 1: 版本与状态前置检查
执行指令1 取版本差异与初始化状态。若已 up-to-date 且已初始化,告知用户并询问是否仍强制刷新 scaffold(确认后继续,cataforge bootstrap 会自动跳过 current 步骤仅跑 doctor),否则结束。
Step 2: 包升级(条件执行)
仅当 Step 1 探测到包落后、或传入 --upgrade-package 时执行;--dry-run 时跳过。依次探测包管理器(短路,找到即停):
uv tool list 2>/dev/null | grep -q cataforge && echo "uv"
pip show cataforge 2>/dev/null | grep -q Name && echo "pip"
uv→uv tool upgrade cataforgepip→pip install --upgrade cataforge- 均未探测到 → 提示用户手动升级包,不 abort,继续 Step 3 仅刷 scaffold(解耦"升级包"与"刷 scaffold")
What ships with it
1 file 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.
- 2d ago First seen · 199 lines · 155 tokens per session scan A e66d44205f88
framework-update is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 155 tokens to every session and 3,002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.