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 Fantasality/dsh-origin-plugin --skill origin-plottinggit clone --depth 1 https://github.com/Fantasality/dsh-origin-pluginWrote 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/fantasality/dsh-origin-plugin/origin-plotting)<a href="https://agentmods.dev/skills/fantasality/dsh-origin-plugin/origin-plotting"><img src="https://agentmods.dev/badge/skills/fantasality/dsh-origin-plugin/origin-plotting/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/fantasality/dsh-origin-plugin/origin-plotting"><img src="https://agentmods.dev/badge/skills/fantasality/dsh-origin-plugin/origin-plotting.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00134 | $0.07201 |
| Opus 5.5 | $0.00054 | $0.02880 |
| Sonnet 5.5 | $0.00027 | $0.01440 |
| Haiku 4.5 | $0.00013 | $0.00720 |
Grade A, and why
origin-plotting 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Origin SOP v2.3.0(决策流驱动;工具挂在步骤下,按序调用)
宿主注入的默认规范(systemPrompt 已带;没有时你按此执行)
- 折线/散点默认
plot_type="line_symbol";未指定导出参数时fmt="png",width=1200。 - 投稿/发表图默认
style_mode="journal"(单栏 89mm / 双栏 183mm),导出width>=1800。 - 轴标题必须语义化:物理量 + 单位(
temperature_C→ "Temperature (°C)"),拒绝 A/B/C 占位名。 - 多组对比 / 列语义不明 / 发表级图:强制
origin_plot_plan→ 用户确认 →origin_execute_plan(见 STEP 3)。
快速路径 vs 正式路径(先选路,再动手)
- 快速路径(数据语义明确、临时查看):
origin_plot_file/origin_load_file+origin_plot,一次调用出图。 - 正式路径(发表级 / 多组对比 / 列语义不明 / 用户没说清):
origin_plot_plan→ 向用户确认 questions →origin_execute_plan→origin_verify_graph→origin_export_delivery。 - 想不起调用链 →
origin_cookbook(离线秒回:quick_plot/from_file/journal/multi_compare/edit/fit/recover/deliver 八场景 + 高频工具推荐默认参数)。
主循环(先看这张图,再往下读)
[0] 提速判断(默认走快路径)
│ 90% 场景:一次 origin_figure 完成 写数/导入→画图→验证→导出(~1s)→ 直接 [7]
│ 只在 需要细改 / 多组对比 / 发表级精修 时才进 [1] 的完整流程
[1] origin_status 检查环境
│ 失败 → origin_diagnose 定位(安装/COM/残留进程/目录权限)→ 按 recovery 修复
│ 读用户意图,四选一分流:
├─ 画新图 ────────────────→ [3] 规划(歧义/发表级/多组对比强制 plan 确认流)
│ └→ [4A] 粗粒度建图 → [5]
├─ 改已画好的图 ─→ [2] inspect_graph 拿现状 → [4B] 细粒度编辑 → [5]
├─ 关窗/整理/激活 ─→ origin_manage_pages 一步完成 → 直接结束
└─ 只要数字不要图 ─→ 附录B 分析工具 / origin-stats skill,结果直接回复用户
[5] origin_verify_graph ── pass/warn → [7]
└── fail → [6] 按错误码修复 → 回 [5](同一问题 2 轮仍 fail:停止重试,如实报告)
[7] 交付:export_delivery / export / save_project → 回复用户路径 + verify 结论
STEP 0 铁律(每条都对应实测过的返工,违反必出错)
- 写后必读返回:所有编辑工具逐项返回 status,必须逐项看(判读见 4B)。
- 改图前必 inspect:曲线索引/图层号/页面短名以
origin_inspect_graph/origin_list_pages读到的为准,不要猜。 - 不虚构数据:列用途有歧义 → 走 [3] 的 plan 确认流,questions 非空必须先问用户;不补造缺失值。
- 引用原样传递:
origin_write_data/origin_load_file返回worksheet,origin_plot*返回graph;后续调用直接传返回值。 - 细粒度修改只用
origin_edit_*/origin_manage_pages,不要绕道自拼 LabTalk(原因见附录 C——裸 LabTalk 会在非活动窗口上静默失败)。 - 正式交付前必过
origin_verify_graph;fail项修完才允许交付。 - 同签名重新 plan 过就别执行旧计划:
origin_execute_plan会校验(plan_stale);确实要执行旧计划传force=true。 - 每次调用返回都带
trace_id+duration_ms:向用户报告故障时附上,便于定位失败阶段。
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 Changed · +3 lines 02469f756d95
- 1mo ago Changed · +95 lines · +41 tokens per session 18f0c077cdf6
- 1mo ago Changed · +78 lines · +36 tokens per session 28f4cf2a8fff
- 1mo ago First seen · 88 lines · 57 tokens per session scan A bb0f44cc15e4
origin-plotting is a skill published in the GitHub repository Fantasality/dsh-origin-plugin (25 stars, last pushed 5d ago), licensed MIT. It adds 134 tokens to every session and 7,201 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
agent-figure-gallery
Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action.
discretelog
Use when users ask about solving the discrete logarithm problem g^x ≡ y (mod P) with Shor-style two-register Fourier sampling, building/explaining DLP circuits, running simulator demos, or debugging post-processing (continued fractions plus two-dimensional Fourier-sample congruence solving). Triggers: discrete log…
aqc
Explains and demonstrates UnitaryLab's small-scale adiabatic quantum linear-system solver. Use it for AQC or QLSP questions, simulator examples, and work involving Householder state preparation, SVD block encoding, adiabatic schedules, post-selection, solution rescaling, or residual checks.
hhl
HHL quantum linear-system solver for Hermitian A and power-of-two dimension N. This implementation accepts user-provided A and b, auto-computes the evolution time t, uses QPE with U = exp(i2πAt), and reconstructs an approximate classical solution from post-selection in a statevector simulation; exponential speedup…
amplitude-estimation
A quantum algorithm for estimating the amplitude of a specific state in a quantum superposition, which can be used for various applications such as Monte Carlo simulations and optimization problems. Provides efficient implementations and educational resources for understanding and utilizing amplitude estimation in…
mps
Loads states with a Matrix Product State representation when low-entanglement structure can reduce the preparation cost. It covers state-to-MPS decomposition, bond-dimension truncation, canonicalization, QR-based unitary completion, work-qubit encoding, leakage, and phase-invariant validation in UnitaryLab.