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 skills/maqitong/hist-bridge/continue-foreignnpx skills add maqitong/hist-bridge --skill continue-foreigngit clone --depth 1 https://github.com/maqitong/hist-bridgeWrote 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/maqitong/hist-bridge/continue-foreign)<a href="https://agentmods.dev/skills/maqitong/hist-bridge/continue-foreign"><img src="https://agentmods.dev/badge/skills/maqitong/hist-bridge/continue-foreign.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 | $0.00110 | $0.00739 |
| Opus 5 | $0.00055 | $0.00369 |
| Sonnet 5 | $0.00022 | $0.00148 |
| Haiku 4.5 | $0.00011 | $0.00074 |
Grade A, and why
continue-foreign 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 4d 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
跨工具续接历史对话
借助 hist-bridge 的 MCP 工具(list_sources / list_conversations / search_conversations / get_conversation / summarize_conversation),把另一个工具里的历史对话接到当前会话继续。典型场景:在 Claude Code 里额度用完,想把 Codex/Cursor/GLM 的某次对话接过来继续问答,或反过来。(注意:在 Cursor 里用 GLM 跑的会话属于 cursor 来源。)
步骤
-
找到目标会话
- 用户说了来源或关键词 →
list_conversations(source=…)或search_conversations(query=…)。 - 没说清 →
list_conversations(limit=15)列最近的,让用户挑序号。先停下等用户确认,别自己猜。
- 用户说了来源或关键词 →
-
载入
- 长会话(消息数 > 60):先调
summarize_conversation拿交接卡(目标/已完成/卡点/待办/最后状态),省上下文。需要细节再get_conversation带max_messages取最近若干条。 - 短会话:直接
get_conversation。 - 想要结构化数据而非 markdown 时用
format: "json"。
- 长会话(消息数 > 60):先调
-
梳理(关键) 载入后,先输出一段简短交接摘要,不要直接埋头干:
- 目标:这次对话本来要解决什么。
- 已完成 / 进行中 / 未完成:把任务拆成这三类,逐条标。
- 卡点:上次停在哪、为什么停(报错、超时、等用户)。
- 下一步:最靠前的那个未完成动作。
-
继续
- 把历史 transcript 当作自己之前的上下文,从「下一步」接着做。
- 需要的话用
list_sources确认哪些来源可用(GLM 默认关闭,需先配 root)。
边界(诚实告知用户)
- 这是上下文接力,不是完整状态重放。被搬过来的只有对话文本——原工具的工具执行状态、MCP/权限状态、子 agent、隐藏推理都没了。要重新跑的命令就重新跑。
- 历史会话的 cwd 可能与当前不同;动手改文件前先核对项目路径。
- 模型差异:从 GLM/Codex 搬来的对话里,对方模型的工具调用格式已被归一化为可读文本,不保证逐字还原。
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.
- 4d ago First seen · 37 lines · 110 tokens per session scan A 555947500ecc
continue-foreign is a skill published in the GitHub repository maqitong/hist-bridge (0 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 739 once invoked, about $0.0006 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…