claudemods
中文English

来源wrg32786/aigent-os

wrg32786/aigent-os 已索引

Claude Code harness that refreshes its own context instead of compacting: at a threshold it writes a verified capsule, runs /clear, and resumes in a fresh session. Memory is plain markdown in git, readable with git log. MIT, runs locally, one install (Node 18+). Codex adapter included.

查看上游仓库

已索引 索引里有这个仓库的包记录。包数量是历史登记记录，不代表这些包现在仍可用。

仓库

规范名称
wrg32786/aigent-os
GitHub 仓库 ID
1269497012
包记录
75 （历史登记记录，不代表现在仍可用）

发现与队列

首个记录来源
search:topic:claude-code-hooks fork:false
发现于
队列状态
ok
记录的错误次数
0
最近完成的处理
下次检查资格
起具备资格

首个记录来源是队列第一次保存的来源，不是完整的发现历史。错误次数在处理以错误状态结束时增加，成功处理后清零，不是全部尝试次数。「最近完成的处理」是结束时间，不是开始时间。

资格按 计算。它不是排期：采集器每次运行只处理有限数量的来源，具备资格也不保证何时检查。

最近保存的扫描

仓库元数据读取于
扫描状态
complete
扫描保存于
识别器版本
2
续扫记录
没有

扫描记录与队列状态分开：队列状态说明处理进度，扫描记录说明最近一次保存了什么。有续扫记录只表示存有未完成的状态，没有剩余数量。

源文件证据覆盖

已存储的包版本在这个仓库中引用的固定源文件的原始计数。它反映已记录了什么，不代表仓库有多完整。

范围与限制

统计所有已存储版本（来自任何包）中指向本仓库规范名称的不同固定文件链接（仓库、提交、路径）。本仓库所拥有的包的文件，只有被某个版本在这里链接时才会计入。不合并别名，也不会根据当前名称推测历史。

「已知」表示已记录普通文件身份，不表示整个目录或包已被覆盖。不是有效固定文件 URL 的链接不计入。

引用了 75 个固定源文件

  • 75 已知
  • 0 提交中不存在
  • 0 文件列表截断
  • 0 不受支持
  • 0 尚无记录
  • 0 读取失败

按仓库、提交和路径去重；同一路径出现在两个提交中，按两个文件身份计数。不是组件组数。

读取失败的提交 0

尚无记录的文件没有对应的提交读取失败记录。

关联的包 75

按仓库的已验证身份关联。数量是历史登记记录，不是当前可用性。

第 1–20 条，共 75 条结果

  • agent-fitness技能

    Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.

    d770442ee7dc

  • body-check技能

    Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.

    d770442ee7dc

  • brief技能

    Generate a structured delegation brief for any task

    d770442ee7dc

  • Caddy Audit技能

    Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Harden…

    d770442ee7dc

  • Caddy Explain技能

    When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility the…

    d770442ee7dc

  • caddy-enroll技能

    Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".

    d770442ee7dc

  • caddy-mute技能

    Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.

    d770442ee7dc

  • capsule-compact技能

    Compact a long capsule chain. Walks parent_capsule_id backward from a head capsule; if chain >= 5, summarizes oldest 3 into a chain-summary capsule. Manual invocation.

    d770442ee7dc

  • close技能

    Commit the session to durable vault memory and prepare a clean resume point

    d770442ee7dc

  • codex-adapter技能

    Route ONE bounded, mechanical task to the Codex CLI as a non-Claude executor, under the same review-before-merge gate as any other agent-produced diff. Use when the user explicitly asks to hand a task to Codex, or names OpenAI Codex / a no…

    d770442ee7dc

  • cognitive-update技能

    Conservative close-parity updates to GOAL_STACK, BELIEF_STATE, SELF_MODEL, and PROCEDURES. Writes only explicit or mechanically evidenced deltas; ambiguity means no write.

    d770442ee7dc

  • comms-summarize技能

    Echo's comms polling skill. Read an inbox, channel, or message thread and return a structured unread summary — sender, topic, action required, and urgency. Read-only.

    d770442ee7dc

  • compact-note技能

    Mnemosyne's note compaction skill. Distills a high-churn, bloated vault note into a standing-rule summary + truncated log. Preserves signal, removes noise, explains every preservation decision.

    d770442ee7dc

  • context-capsule技能

    The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop. Mid-session checkpoint or completion capsule; a rolling best-effort version of the same write also runs automatically on every …

    d770442ee7dc

  • context-hygiene技能

    Nightly context trim for ACTIVE_PRIORITIES and the dated SESSION_LOG schema. Archives before removal, uses content-hash compare-and-swap, and refuses unknown shapes.

    d770442ee7dc

  • critique-plan技能

    Hypatia's plan critique skill. Takes a strategic plan, architectural decision, or proposal and returns adversarial pre-commitment review — strongest counterargument first, hidden assumptions surfaced, alternatives named.

    d770442ee7dc

  • decide技能

    Run a decision through the 12-lens framework

    d770442ee7dc

  • deep-recon技能

    Run extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angles, or generate a structured recon document.

    d770442ee7dc

  • Diagnose技能

    When something feels off, type /diagnose and describe the symptom. The skill walks the seven-layer stack (kernel, skills, hooks, daemons, vault, doctrine, principal config) and reports which layer is most likely responsible. Caddy pattern …

    d770442ee7dc

  • digest技能

    Review staged memory candidates from MEMORY_CANDIDATES.md. Surface each with promote/skip/supersede options. Does not auto-promote.

    d770442ee7dc

已保存的扫描说明 0

没有保存额外的扫描说明。

记录的别名 0

这些名称在上次记录时指向这个仓库。这是记录下来的解析结果，不是实时的 GitHub 检查；本站不会因此合并包或元数据。

没有记录到指向这个仓库的别名。

不支持的市场条目 0

这个仓库的市场清单里、本站暂不支持的条目。它们是原样保存的来源数据，不会被抓取或执行。

没有记录到不支持的条目。