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 TianLin0509/SuperRAN --skill channel-simgit clone --depth 1 https://github.com/TianLin0509/SuperRANWrote 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/tianlin0509/superran/channel-sim)<a href="https://agentmods.dev/skills/tianlin0509/superran/channel-sim"><img src="https://agentmods.dev/badge/skills/tianlin0509/superran/channel-sim.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 5.1 | $0.00338 | $0.08947 |
| Opus 5 | $0.00169 | $0.04473 |
| Sonnet 5 | $0.00068 | $0.01789 |
| Haiku 4.5 | $0.00034 | $0.00895 |
Grade A, and why
channel-sim 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.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
无线信道仿真编排
配合 superran MCP(35 个 sr_* 工具)使用。MCP 提供能力与数据,
本 skill 负责把仿真条件定清楚、把实验做公平、把结论守住。
过不了门时,如实说明拦在哪一项,让用户决定是修还是接受局限。不要绕过:
- 不许用"总体来看""趋势上""大部分样本呈现正向""量级上"把没过的门糊过去; 也不许把"不显著"重新框成"找到了适用边界""稳定的正向趋势"。换壳不是换结论。
- 不许把数字给出去再补一句"未做检验/仅供参考"——加限定词不等于过门。 那句话不传递可行动信息,只让你事后能说"我提醒过"。也不许把两个单臂数字并排摆着 让读者自己做减法:语法上不是比较,读者带走的还是那个差,形式规避比直接违规更坏。
- 不许拿"用户是专家""他授权了""责任在他"当理由。你出的那个数会被引用, 用户能豁免的是自己的判断,豁免不了这个数是怎么算出来的。
- 不许换个检验、换个指标、换个子集重报。挑赢的那个就是 p-hacking。
- 不许自己手算一个工具没跑过的检验(符号检验、bootstrap、事后分组)来救门。 手算的 p 值、手推的样本量与标准误一律不许写进正文。
- 不许把"效应方向成立、幅度未确立"拆开说。方向也是结论,门 3 没过就是都没有。
statement 说不成立就照抄那句话。 旁边可以补:效应量点估计、置信区间、
下一步要多少样本(由 sr_sample_size 算)、失败样本值得分组看。不可以改写它本身,
也不可以让读者从这一段带走"做出来了"的印象。哪句话需要哪份证据 →
references/gates-and-stats.md 的「声称与证据」表。
Checklist
只建这 4 个任务,不要把下面的内务步骤也建成任务。
- 对齐目标 —— 问清要什么、跟什么比、看什么指标,落成计划书 + 说明书
- 生成数据 —— 按计划书生成,并自检这批数据能不能用
- 跑对比 —— 内置方案横评、系统级仿真,或接用户自己的算法
- 写结论 —— 只写证据支持的话
sr_lock_analysis、sr_probe_scenario、sr_gate、sr_sample_size、门 2、门 3
这些一律不建任务——它们是内务,照做但不占用户的注意力,做完在所属那一步的
汇报里带一句就行("门 1 全过")。
不许把这 4 步拆细、加前缀编号、或者再嵌一层子任务。 早先的十步清单实测让用户明确反感。以下都不是例外:
- 用户说"我盯着进度 / 别让我不知道你在干嘛"——可见性靠对话汇报,不靠条数。 开始一件耗时的事说一句、结束再说一句,比 10 条待办有用得多。
- "需要用户动手的交接点值得单独列一条"——不列。直接说"你今天只需在两处动手"。
- "我不是按工具拆的,我按
能失败/能卡住用户/是个决定点筛的"——筛法不重要,条数 才重要。 "TodoWrite 不支持嵌套,所以我平铺 + 加阶段前缀"也一样:那就是拆细。 - 门 1 不过要回头重生成、清单会分叉——4 条粗任务正是为了吸收分叉,不是缺点。
- 也不许在过程中改写任务文案制造进度感("生成数据(已 120/200)")。进度发在对话
里,条目从建好到打勾一个字不改——门 1 拦在哪一项、
notes的告警只在对话里。
流程图
digraph channel_sim {
rankdir=LR;
node [shape=box]; edge [color="#666"];
subgraph cluster_0 { label="1 对齐目标"; style=rounded; color="#888";
"问 + 计划书"; "锁口径" [style=dashed]; }
subgraph cluster_1 { label="2 生成数据"; style=rounded; color="#888";
"探场景" [style=dashed]; "生成"; "门1 信道可信?" [shape=diamond, style=dashed]; }
subgraph cluster_2 { label="3 跑对比"; style=rounded; color="#888";
"定样本量" [style=dashed]; "横评 / 系统级 / 外部算法"; "门2 门3" [shape=diamond, style=dashed]; }
"写结论" [shape=doublecircle];
"问 + 计划书" -> "锁口径" -> "探场景" -> "生成" -> "门1 信道可信?";
"门1 信道可信?" -> "问 + 计划书" [label="不通过"];
"门1 信道可信?" -> "定样本量" [label="通过"];
"定样本量" -> "生成" [label="样本不够"];
"定样本量" -> "横评 / 系统级 / 外部算法" -> "门2 门3";
"门2 门3" -> "横评 / 系统级 / 外部算法" [label="不公平/不显著"];
"门2 门3" -> "写结论" [label="通过"];
}
What ships with it
9 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/asking.md 4.6 KB
- references/default-hardware.md 3.2 KB
- references/gates-and-stats.md 11 KB
- references/link-adaptation.md 7.5 KB
- references/performance.md 4.7 KB
- references/pressure-tests.md 19 KB
- references/scenarios-and-interference.md 5.1 KB
- references/spec-sheet.md 4.3 KB
- references/system-sim.md 48 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.
- yesterday Changed · +10 lines 97f8a695d4fc
- 3d ago Changed · +3 lines 72b935618d79
- 4d ago Changed · -145 lines · +93 tokens per session 72b59f97f428
- 8d ago First seen · 474 lines · 245 tokens per session scan A 2e4b23c7f258
channel-sim is a skill published in the GitHub repository TianLin0509/SuperRAN (2 stars, last pushed 3d ago), licensed MIT. It adds 338 tokens to every session and 8,947 once invoked, about $0.0017 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 2026-08-31.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
ruview-advanced-sensing
Advanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, persistent field model), cross-viewpoint fusion across multiple nodes, RF tomography (ISTA L1 solver, voxel grids), longitudinal biomechanics drift, pre-movement intention signals, adversarial signal detection…
ruview-applications
Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
opentrons-integration
Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…
pylabrobot
Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.