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/chat_agentnpx skills add deeleeramone/PyWry --skill chat_agentgit 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 | $0.01784 |
| Opus 5 | $0.00017 | $0.00892 |
| Sonnet 5 | $0.00007 | $0.00357 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
chat_agent 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chat — Agent Operating Manual
You are running INSIDE a PyWry chat widget. This skill is not about creating a chat — it's about operating correctly when the chat is the UI you're attached to.
Where your input comes from
The user types a message; the chat manager packages it and passes it
to your provider (DeepagentProvider or equivalent). You receive:
- text — the user's literal message
- attachments — any
@<name>context the user inlined, expanded into a block prepended to the message - thread history — the running conversation stored against a
session_id/thread_idkeyed checkpointer
Your reply is streamed token-by-token into the UI. Tool calls you make are shown as collapsible tool-result cards in the chat.
The @<name> attachment format
When the user types @chart (or any other registered context
source), the chat manager prepends a block to the message like:
--- Attached: chart ---
widget_id: chart
<...any additional component context...>
--- End Attached ---
<the user's actual text>
The first line after the marker is ALWAYS widget_id: <id> for
widget attachments. Read that value out and use it as the
widget_id argument on every tool call for this turn. Never
guess — the attachment is the source of truth.
If the user references a widget without attaching it, either:
- Call
list_widgets()to look it up by name. - Ask the user to attach it (
"Type @chart so I know which widget you mean.").
Do NOT invent a widget_id.
Auto-attached context sources
Some examples register context sources that get auto-attached to
every user message. In that case you'll see the --- Attached ---
block even when the user didn't explicitly type @<name>. Treat
it the same way — read widget_id and use it.
Tool-call result cards
Every tool call you make is rendered in the chat as a card showing:
- Tool name (e.g.
tvchart_symbol_search) - Status — spinner while running, ✓ on success, ✗ on failure
- Collapsible payload: arguments in, result out
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 · 190 lines · 34 tokens per session scan A bdd6735fbe83
chat_agent 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 1,784 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…