Borrowing it
Nothing to install: this file belongs to tt-11-dd/tether-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tt-11-dd/tether-ai/main/.agents/skills/init-long-run/SKILL.mdgit clone --depth 1 https://github.com/tt-11-dd/tether-aiWrote 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/tt-11-dd/tether-ai/init-long-run)<a href="https://agentmods.dev/skills/tt-11-dd/tether-ai/init-long-run"><img src="https://agentmods.dev/badge/skills/tt-11-dd/tether-ai/init-long-run/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/tt-11-dd/tether-ai/init-long-run"><img src="https://agentmods.dev/badge/skills/tt-11-dd/tether-ai/init-long-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00258 |
| Opus 5 | $0.00022 | $0.00129 |
| Sonnet 5 | $0.00009 | $0.00052 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
init-long-run 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 9d 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.
What it actually says
初始化跨会话任务
只在用户明确要跨会话做、或点了「拆成可跨会话的任务清单」时使用。普通问答不要跑。
- 只读：当前工作目录、README、
AGENTS.md/CLAUDE.md、相关入口。不要 write / edit / patch 业务代码。 - 按用户目标写出
.agents/features.json：JSON 数组，每项{ "id", "description", "passes": false }。条目要能单独验收，不要一项里塞整盘改造。 - 写出
.agents/progress.md，第一段写：摸了什么、清单在哪、下一轮该做哪一条。 - 若已有 git 仓库，做一次提交，说明是初始化任务清单。没有 git 就跳过。
- 停。告诉用户下一轮用 continue-long-run，一次只做一条。
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.
- 9d ago First seen · 15 lines · 44 tokens per session scan A bd53d36273a6
init-long-run is a skill published in the GitHub repository tt-11-dd/tether-ai (82 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 258 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
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
memory-compounding
Review and sharpen persistent memory so it compounds instead of accumulating. Use when pruning pi-hermes-memory entries, doing monthly memory hygiene, or when the same lesson has been recorded multiple times.
bearings
Generate a "pick up where I left off" status report across all active Pi sessions. Use when the user asks for bearings, a status report, morning brief, catch-up, "where did I leave off", or "what's in the works". Reads live session state, composes a scannable 4-section digest, and writes a dated report to…
effect-rpc-cluster
Build typed RPC endpoints and cluster-distributed entities, singletons, cron jobs, and durable workflows with Effect's RPC and Cluster modules (Rpc/RpcGroup/RpcServer/RpcClient, Entity/Sharding/Singleton, Node/Bun bundles). Use when building RPC services or distributed/clustered Effect systems.
effect-error-handling
Implement typed error handling in Effect v4 using Schema.TaggedErrorClass, catchTag/catchTags, catchReason/catchReasons, Cause, ErrorReporter, and recovery patterns. Use this skill when working with Effect error channels, handling expected failures, or designing error recovery strategies.
effect-http-api
Build typed HTTP APIs with Effect's HttpApi — endpoints with schemas, handlers, security middleware, OpenAPI docs, derived clients, and handler unit tests. Use when building HTTP servers, REST APIs, or typed HTTP clients with Effect v4.