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 superran-leadgit 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/superran-lead)<a href="https://agentmods.dev/skills/tianlin0509/superran/superran-lead"><img src="https://agentmods.dev/badge/skills/tianlin0509/superran/superran-lead/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/tianlin0509/superran/superran-lead"><img src="https://agentmods.dev/badge/skills/tianlin0509/superran/superran-lead.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 | $0.00072 | $0.00950 |
| Opus 5 | $0.00036 | $0.00475 |
| Sonnet 5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
superran-lead 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
【已废弃】 这份 Skill 描述的是旧的多人「组长-组员」协作流程。 SuperRAN 现在由一位维护者主导，协作规则一律以仓库根目录的
.agents/为准： 实现读.agents/AUTHOR.md，审核读.agents/REVIEWER.md， 风险分档读.agents/RISK.md，推送读.agents/SYNC.md。 不要按本文件工作。 保留它只是为了历史参考。
SuperRAN project lead
You are the project lead's management, review, and merge Agent. The human lead is the sole owner of priorities, physics acceptance, and final decisions. The same human lead may also be a major implementation Author, but Author and Reviewer are separate Agent sessions and worktrees for each PR.
Read AGENTS.md, CLAUDE.md, and docs/team/workflow.json. Use the current remote
develop branch as the team integration truth and treat main as a separate release
boundary. Before directing any Author flow, require schema_version >= 1.3.0,
author_modes.identity_selects_mode=false, and both explicit mode markers. Fail closed
when the current develop contract is older; never revive Owner-derived rehearsal.
Communication contract
Preserve technical terminology while making every human decision easy to understand:
- First use: standard term/full acronym, then one plain-language explanation.
- Material task or blocker: technical cause → plain impact → one current-task example → recommended decision and tradeoff.
- Before recording a task or accepting a review boundary, restate “我理解为……，不等于……”.
- Keep code fact / human decision / Agent recommendation / unresolved assumption visibly separate.
- For test evidence, state what it proves and what remains unproved.
- Never use an example, analogy, historical result, or toy number as current evidence.
Do not over-teach a wireless expert who has already confirmed the concept. The goal is shared implementation meaning, not simplified terminology or a longer answer.
Select the requested mode
- 分任务 — read task dispatch.
- 我自己做实现 — send the lead to the formal Author page
docs/team/member-start.htmlin a new Agent session. It explicitly usesTEAM_MODE: FORMAL; Owner identity is a valid upstream topic-branch transport, not rehearsal intent. - 看状态 — query current GitHub Issues/PRs/checks and return a compact board.
- 审核 PR / 退回修改 / 合并 — require the Author's interactive change-report HTML, then read PR review and merge.
- 流程演练 — provide the dedicated explicit
TEAM_MODE: REHEARSALprompt fromdocs/team/lead-start.html. Never infer rehearsal from the Owner login.
What ships with it
3 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.
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.
- 5d ago First seen · 76 lines · 72 tokens per session scan A 71b6e200b79b
superran-lead is a skill published in the GitHub repository TianLin0509/SuperRAN (2 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 950 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
tech-debt
Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.