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/deeleeramone/pywry/eventsnpx skills add deeleeramone/PyWry --skill eventsgit clone --depth 1 https://github.com/deeleeramone/PyWryWhat 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 | $0.00034 | $0.01388 |
| Opus 5 | $0.00017 | $0.00694 |
| Sonnet 5 | $0.00007 | $0.00278 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
events 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 3d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyWry Event System — Agent Reference
The event bus is the plumbing underneath every MCP tool. You rarely need to think about it — the typed tools wrap emit + wait + state-poll for you — but when you reach for
send_eventor interpret tool results, this is how it works.
Event names are namespaced
Every event has the form namespace:event-name, e.g.:
tvchart:symbol-search— ask the chart to open symbol searchtvchart:state-response— chart's reply with its current statetvchart:data-request— chart asks Python for barstvchart:data-response— Python delivers barstoolbar:request-state— ask a toolbar component for its valuetoolbar:state-response— component's replychat:user-message— user typed somethingchat:ai-response— model produced a tokenpywry:update-theme— dark/light mode change
Never emit an event with a name that doesn't match namespace:event-name
— the framework rejects it.
Widget IDs vs component IDs
widget_id — identifies the top-level PyWry widget (a chart, a grid,
a chat panel, a dashboard). Every MCP tool takes widget_id as an
argument because all events route to the widget first.
componentId — identifies a child inside a widget (a specific toolbar button, a marquee ticker slot, a chart pane). Component IDs are scoped to their containing widget.
When you call send_event(widget_id, event_type, data), the
widget_id picks the target widget; anything identifying a specific
component goes in the data payload (typically as data.componentId
or data.chartId).
Request / response pattern
Some events are fire-and-forget (e.g. tvchart:symbol-search —
"please do this"). Others are request/response round-trips where the
caller wants a reply (e.g. tvchart:request-state → tvchart:state-response).
The framework correlates request/response with a context token:
- Emitter generates a random
contexttoken. - Emitter injects it into the request payload.
- Listener sees the request, attaches the same
contextto its response, and emits the response event. - Emitter sees the matching
contexton the response and wakes up.
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.
- 3d ago First seen · 152 lines · 34 tokens per session scan A cc5045c47ab9
events is a skill published in the GitHub repository deeleeramone/PyWry (93 stars, last pushed 9d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,388 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
dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…
codex-review-loop
Adversarial PR code review using Codex CLI. Codex review (20-50 min) -> structured findings -> HITL approval -> fix loop.
data-access
A 股零鉴权取数手册。当需要真实的行情 / 市值 / 估值快照、季度报告期累计财务数据、机构一致预期 EPS、PE 历史序列、公告标题、日 K 线、交易日历时使用;只允许运行本 skill 登记的脚本取数(腾讯 / 新浪 / 同花顺 / baostock / 深交所 / 东财),禁止凭模型记忆给数,禁止自造爬虫。概念解释、观点讨论等不需要取数的话题不要加载。.
industry-chain
产业链下钻与不可替代性判定方法:以龙头为"需求入口"沿供应链逐层下钻(整机 / 龙头 → 部件 → 核心器件 → 材料 → 衬底与设备),用物理 / 材料约束(扩产周期、良率、认证周期、有无替代)当筛子找供给刚性的卡口;给每个标的贴不可替代性标签(techmoat / capacitymoat / both / 待补)并列证据;含"卡口越硬越贵"与预期差四问的校准。当任务涉及产业链位置、上下游、护城河、不可替代性、供给瓶颈、竞争格局时加载;单纯取数、估值计算、财报拆分等不涉及产业链结构的任务不要加载。只产出框架与证据表,不给投资动作建议。.
verify-changes
Verify a code change in this repo before committing or opening a PR. Use after editing collector (backend), web (frontend), shared package, or the Go agent — picks the minimal sufficient check set per touched area.
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to…