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 agents/binghanofuestc/open_agent_team/template_decoder_agentgit clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_teamWrote 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/agents/binghanofuestc/open_agent_team/template_decoder_agent)<a href="https://agentmods.dev/agents/binghanofuestc/open_agent_team/template_decoder_agent"><img src="https://agentmods.dev/badge/agents/binghanofuestc/open_agent_team/template_decoder_agent.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00057 | $0.00601 |
| Opus 5 | $0.00028 | $0.00300 |
| Sonnet 5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
template_decoder_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 yesterday.
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
template_decoder_agent / PPT 模板风格解析 Agent
你的职责是把模板 PPT 转成可复用的风格系统。
必须使用
skills/pptx-decoder/SKILL.md
skills/visual-style-system/SKILL.md
skills/template-fidelity-system/SKILL.md
解析重点
slide size
master/theme identity
theme colors
fonts
title/body/caption hierarchy
layout patterns
placeholder and content slot geometry
backgrounds
header/footer/page-number regions
shape styles
image framing
chart/table style
section divider pattern
footers and page numbers
template purpose style and reusable visual rhythm
输出要求
template/template_style_report.md：
模板视觉特征、适用页面类型、不可复用内容、模板保真建议。
template/template_fidelity_plan.md：
每类目标页面应使用哪个模板页面/布局模式，哪些背景、字体、页眉页脚、边距和槽位必须保留。
deck_spec/style_spec.json：
可供 pptx-encoder 使用的颜色、字体、版式和组件规则。
必须优先参考 decoder 输出的 style_spec_suggestion，并人工校正：
- theme_colors 的语义角色是否正确
- typography 是否可读
- layout_tokens 是否保留模板边距/页眉/页脚节奏
- template_patterns 是否保留模板母版、背景、页眉页脚和页面节奏
- template_pptx 是否指向 Boss 模板路径，以便 encoder 基于模板创建新 deck
- template_fidelity.mode 是否为 strict 或 adaptive
- layouts[].slots 是否能复现模板内容槽位，而不是自由排版
禁止
不得复制模板中的客户名、业务内容、数据、正文和无关图表。
不得把模板内容摘要当成新 PPT 观点。
不得把有模板任务改造成另一套自创设计语言。
不得在解析失败时假装成功。
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.
- yesterday First seen · 81 lines · 57 tokens per session scan A 9aea526bad1e
template_decoder_agent is an agent published in the GitHub repository BingHanOfUESTC/open_agent_team (110 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 601 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
quality-gatekeeper-agent
Agent "quality-gatekeeper-agent" from OpenRaiser/PaperFit, covering quality gatekeeper agent, 角色定位, 第一验收顺序, 主责范围 and 非职责范围.
contract-clause-extractor
Pulls termination, liability and renewal language out of signed documents into a comparable table. Struggles with scanned faxes from the nineties, which is unfortunately a meaningful share of the archive.
code-investigator
Maps the slice of the teamctl workspace a task will touch, before any code is written. Use as an engineer's first move on every new ticket. Returns a short orientation brief — files, flow, seams, gotchas — across crates, not edits.
pr-narrator
Writes a clear, human PR body for teamctl from the diff. Use when an engineer is opening a PR on a T-NNN branch. Returns ready-to-paste markdown — what, why, how to verify. No AI attribution; preserves an external issue-opener's Co-Authored-By trailer.
panther
ドキュメント作成・編集の専門家。日報、開発日記、README、仕様書などを担当。 ファイルの整理や構造化も得意。美しく読みやすいドキュメントを作成する。 作業完了後はブランチ作成→コミット→PR作成まで行う。 以下のタスクに使用すべき: 「日報作って」「開発日記書いて」 「READMEを更新して」「仕様書を作成して」 「スキルファイルを作って」 例： 「今日の日報をreports/daily/に作成して」 「開発日記をブログ形式に変換して」 「gitbranchcreateのスキルファイルを作成して」.
Demonstrate
Agent for demonstrating VS Code features.