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/contextnpx skills add lync-cyber/CataForge --skill contextgit 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 | $0.00074 | $0.00823 |
| Opus 5 | $0.00037 | $0.00411 |
| Sonnet 5 | $0.00015 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
context 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.
What it actually says
统一上下文 I/O (context)
文档生命周期的单一能力入口(cataforge context,其文件后端引擎为 cataforge docs),后端路由纪律见 COMMON-RULES §Agent 文档 I/O 契约。后端能力非对称:读取/生成/校验按方案路由且在后端不可达时降级;关系追溯(query 分支)是图原生能力,需图后端就绪(无对等文件回退)。
能力边界
- 能做: 按需加载章节/实体、依赖与追溯查询、文档生成与写入、单文档与跨文档门禁校验
- 不做: 内容决策(由调用 Agent 负责)、代码审查(由 code-review 负责)、框架元资产审查(由 framework-review 负责)
输入规范
- 操作分支:
navigate|generate|review|consistency|query - 引用:
doc_id#§N[.item](格式见 COMMON-RULES §文档引用格式) - 各分支的参数与命令见对应 reference 文件
输出规范
- 读取: 目标章节/实体内容(markdown 形式,后端无关)
- 查询: 依赖/追溯结果
- 生成/写入: authoring 落图 + 定稿导出路径
- 校验: 审查/一致性报告 + 三态结论
操作指令
按意图选分支,详见 reference:
- navigate — 按需读取章节/实体、依赖展开、token 预算。见 references/navigate.md
- generate — 取模板、authoring 落图、定稿导出、拆分。见 references/generate.md
- review — 单文档门禁(脚本检查 + 语义审查)。见 references/review.md
- consistency — 跨文档一致性(覆盖矩阵、契约对齐)。见 references/consistency.md
- query — 自然语言追溯查询。见 references/query.md
Anti-Patterns
- 禁止: 一次性 Read 超过 200 行的整篇文档 — 按章节/条目加载是核心价值,全文 Read 吃掉数千 token 还引入无关噪声
- 禁止: 在调用面判断"该走哪个后端" — 后端选择由框架路由,prompt 里复述分发条件会随实现漂移
- 禁止: 跳过 generate 的定稿步骤直接退出 — 定稿负责持久化与事件写入,跳过会让后续读取/校验找不到新内容
- 避免: 同一会话重复加载同一章节 — 内容已在上下文,重复加载浪费 turn 和 token
What ships with it
23 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.
- references/consistency.md 1.3 KB
- references/generate.md 3.1 KB
- references/navigate.md 1.2 KB
- references/query.md 1.5 KB
- references/review-arch.md 2.7 KB
- references/review-prd.md 2.5 KB
- references/review-ui-spec.md 2.5 KB
- references/review.md 3.2 KB
- templates/_registry.yaml 3.0 KB
- templates/lite/arch-lite.md 1.6 KB
- templates/lite/dev-plan-lite.md 1.8 KB
- templates/lite/prd-lite.md 1.4 KB
- templates/lite/ui-spec-lite.md 2.1 KB
- templates/prototype/brief.md 2.7 KB
- templates/standard/arch.md 3.3 KB
- templates/standard/deploy-spec.md 1.3 KB
- templates/standard/dev-plan.md 3.5 KB
- templates/standard/prd.md 1.3 KB
- templates/standard/test-report.md 1.4 KB
- templates/standard/ui-spec.md 3.2 KB
- templates/utility/changelog.md 266 B
- templates/utility/research-note.md 650 B
- templates/utility/sprint-review.md 1.6 KB
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 · 44 lines · 74 tokens per session scan A c1b8b8ba12e9
context is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 823 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 2026-08-30.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…