Kucell

agent-dashboard

Generate a local HTML dashboard for task progress, worktree collaboration, active agents, locks, handoffs, and recommended next actions.

architecture-guard

Guards project architecture through automated audits and manual reviews. Ensures code changes comply with architectural principles defined in `.agent/rules/architecture-design.md`.

context-budget

基于 L0/L1/L2 分层摘要的上下文预算控制（受 OpenViking 启发）。从 `.agent/references/` 中按 L0 关键词筛选、L1 排序、最后才加载 L2 全文，将注入量控制在模型上下文窗口的 40% 以内。零额外 token（前端启发式），输出 context-manifest.json + retrieval trajectory。

handoff

创建或恢复人可读与机器可读的轻量任务交接产物，用于在不同 Agent、会话或 sub-agent 之间转移工作，同时避免复制大型产物。

management-api

Cortex Agent dashboard、runs、queues、sessions、inbox、decisions 和 waitpoints 的本地管理查询与受控运行态写入器。

maturity-tracker

Harness 组件成熟度追踪。在 /ship CLEAN 阶段收集各组件表现指标，写入 metrics/component-health.json，供 /briefing 展示成熟度看板和退化决策依据。

phase-gate

State machine gate checker for workflow phase transitions. Ensures hard preconditions are met before moving to next phase.

validation-contract

Create, check, and summarize executable validation contracts for Mission Lite milestones and high-risk tasks before implementation begins.

Cross-store hybrid lexical retrieval, bidirectional [[wikilink]] backlinks, and rename-tracking over the .agent/ knowledge bases. Zero dependency. Use to find relevant knowledge across memory/experiences/references/decisions, discover who links to a note, or safely rewrite links after renaming a note.

subagent-trace

Receiver for sub-agent fan-out lifecycle events. Hosts (Claude Code / Cursor / Codex) push spawned / progress / completed / cancelled via `emit`; this skill appends to runs/<id>.json#subagent_fanout[] AND

Data & Documents Listed

evolution-pipeline

OpenViking 风格的异步自我进化管线。Session 归档 (`runtime-continuity/archive`) 后自动 enqueue，worker 后台提取 observation 写入 `.agent/memory/{feedback,project,experiences}/`。零 LLM 依赖（v1）。

resource-ingest

External resource ingestion (inspired by OpenViking's `client.add_resource`). Pull URL / file / git repo into `.agent/resources/external/`, auto-generate L0/L1, register in context-index.json + uri-map.json + MANIFEST.json. Zero LLM dependency.

retrieval-trajectory

Record and replay retrieval trajectories (inspired by OpenViking's observable retrieval). After every context-budget / knowledge-retrieval / skill-selector execution, writes `.agent/runtime-evidence/trajectory/{task-id}_{ts}.jsonl`. Supports replay, URI resolution verification, and fixture export.

secrets

凭据存储抽象 — 用 `secret://<ref>` 语义引用代替明文 token;支持 macOS Keychain、Linux Secret Service、gpg-encrypted file、env 4 个可插拔后端;agent 永不接触明文值,由框架代为取 + 注入。

session-triage

Decide whether to open a Mission + Run based on session signals (turns, debug keywords, tool failures). Open, observe, record-tool. Keeps active-task persistence automatic per `runtime-state-required`.

Data & Documents Listed

uri-resolver

Resolve `cortex://` URIs and `.agent/` filesystem paths bidirectionally. Audits `.agent/` markdown for relative references. Inspired by OpenViking's `viking://` protocol. All new `.agent/` documentation should prefer `cortex://` form so cross-project copies don't require path rewrites.

vcs-pr

VCS Pull Request 创建 / 状态 / 合并 — 通过 secret://<ref> 间接 token,框架代为取 + 注入 Authorization header;agent 永不接触明文。可插拔 backend:gitea / github / gitlab。

branch-namespace

当多个 clone 或 worktree 共享同一份 .agent 时，可选地将分支本地 plans、missions、handoffs 和 incidents 路由到防碰撞命名空间。

Data & Documents Listed

graphify

查询当前项目的 Graphify 知识图谱。支持 query（关键词检索）、path（两文件最短路径）、explain（节点解释）、extract（子图提取）。需要 graphify-out/graph.json 存在。

runtime-evidence

初始化和维护运行时验证证据文件，供 /briefing、/ship 和 validation-contract 判断验证状态。

runtime-state-integration

判定功能属于有状态或可豁免，创建并检查七部分运行态集成契约，并汇总验证缺口。用于架构、规划、Mission、实现评审或交付包含生命周期、持久化、副作用、恢复、查询界面或持久证据的功能。

agent-review-benchmark

Generate evidence-linked Guided Review artifacts and deterministic local Agent benchmark summaries. Use when reviewing Agent-produced diffs by intent, recording structured follow-ups, comparing multiple Agent/model/configuration runs against versioned repository assertions, or preparing reproducible review and benchmark evidence for /ship or Mission validation.