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 lync-cyber/CataForge --skill framework-walkthroughgit 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/framework-walkthrough)<a href="https://agentmods.dev/skills/lync-cyber/cataforge/framework-walkthrough"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/framework-walkthrough/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/lync-cyber/cataforge/framework-walkthrough"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/framework-walkthrough.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 14 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 23 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 34 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 74 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00185 | $0.03295 |
| Opus 5.5 | $0.00074 | $0.01318 |
| Sonnet 5.5 | $0.00037 | $0.00659 |
| Haiku 4.5 | $0.00018 | $0.00330 |
Grade A, and why
framework-walkthrough 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目走查 (framework-walkthrough)
能力边界
- 能做: 在隔离沙盒里部署目标平台资产并以指定执行模式驱动一个小型示例项目跑通端到端工作流；按
references/runtime-flow-map.md逐路径覆盖完整运行流程的五类路径（初始化 / 核心执行链路 / 分支 / 异常 / 终止清理），在每个阶段/门禁/降级/恢复处采集「观察点」；产出框架本身与走查流程本身两类改进建议报告 + 路径覆盖账本；走查后按references/self-update-protocol.md对 process 类 findings 做自更新闭环（回灌本 skill 的 SKILL.md / references）；跨四端可移植（用能力标识符与cataforgeCLI 而非平台原生名） - 不做: 修改被走查项目的业务资产或本 skill 之外的
.cataforge/本体（framework 类改进只产报告到docs/reviews/framework/；自更新仅限框架仓本体内的skills/framework-walkthrough/子树）；替代 framework-review 的静态元资产审查（互补，发现面不同）；替代 platform-audit 的 IDE 厂商对账；进入业务开发主循环（按需触发）
输入规范
- 可选
--mode: 执行模式，缺省standard（7 阶段全跑，门禁与检查点覆盖面最大）；要快速冒烟时显式--mode agile-lite；语义见 COMMON-RULES §执行模式矩阵 - 可选
--platform: 目标平台，缺省取framework.json#/deployment.default_platform - 可选
--example: 示例目标 id，缺省内置temperature-converter（见references/example-project.md）；要走查 UI 链路（ui_design 真驱动 + UI 保真评审）用temperature-converter-ui；自带目标须小到单轮收敛 - 可选
--depth: 覆盖深度，缺省smoke。smoke只确定性驱动 happy path 主干、对分支/异常路径仅机会观察；full额外按路径图探针清单逐个触发可达的分支/异常路径 - 被走查的框架资产: 项目根
.cataforge/（必读） - 完整运行流程路径图:
references/runtime-flow-map.md；详细执行协议:references/walkthrough-protocol.md；观察与归类口径:references/observation-rubric.md；自更新协议:references/self-update-protocol.md
输出规范
- 走查改进报告:
docs/reviews/framework/FRAMEWORK-REVIEW-walkthrough-{YYYYMMDD}-r{N}.md，front matterdoc_type: framework-review（编号与字段按.cataforge/references/review-report-spec.md） - 报告含: 两类 findings（
framework框架本身缺陷/摩擦 +process走查流程本身可改进项，各按 COMMON-RULES §统一问题分类体系 / §归因分类 与.cataforge/references/review-report-spec.md§问题格式 标注；process 条目附resolution: applied|proposed|deferred）+ 路径覆盖账本（路径图每条路径标 driven / probed / observed / not-reached(原因)，字段见 runtime-flow-map §7） - 自更新变更（若触发）: 对本 skill SKILL.md / references 的修改留在工作区由标准 PR 流程收口，修改摘要记入报告对应 process finding
- 沙盒运行产物: 留在 gitignored 沙盒目录供复核，不入仓；报告以「产物清单 + 关键证据」形式引用
What ships with it
5 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.
- 1mo ago First seen · 85 lines · 185 tokens per session scan A 05cf3b8696ea
framework-walkthrough is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 2mo ago), licensed MIT. It adds 185 tokens to every session and 3,295 once invoked, about $0.0007 per session on Opus 5.5. 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
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.