Agent skill

Knowledge Capacity Lifecycle And Egress

by echoVic in echoVic/blade-code

覆盖 Session、Task、Tool、Provider、Browser 的有界准入,跨 Session 公平性,SSE/ACP/Headless 输出背压,以及取消、关闭和进程树回收。

MITAuto-check passedDevOps & Cloud

Install Knowledge Capacity Lifecycle And Egress

skills CLI
$ npx skills add echoVic/blade-code --skill knowledge-capacity-lifecycle-and-egress -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install echoVic/blade-code knowledge-capacity-lifecycle-and-egress --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.trae/knowledges/workspace-policy-and-shared-foundations/capacity-lifecycle-and-egress .claude/skills/knowledge-capacity-lifecycle-and-egress && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
knowledge-capacity-lifecycle-and-egress
GitHub stars
181
Token cost
~2.4k tokens
SKILL.md length
653 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

覆盖 Session、Task、Tool、Provider、Browser 的有界准入,跨 Session 公平性,SSE/ACP/Headless 输出背压,以及取消、关闭和进程树回收。

  • Tasks that involve Git worktrees
  • SKILL.md covers Module Structure, Branching Table, Affected Scope and Gotchas, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Observability

What it does

Knowledge Capacity Lifecycle And Egress is an agent skill from echoVic/blade-code. 覆盖 Session、Task、Tool、Provider、Browser 的有界准入,跨 Session 公平性,SSE/ACP/Headless 输出背压,以及取消、关闭和进程树回收。 使用时机:排查 429/resourceexhausted、队列饥饿、内存增长、输出乱序、Session 驱逐、Browser 容量、关闭挂起或孤儿进程。 不包含:Provider 重试/熔断算法见 model-and-provider-runtime/provider-resilience-admission-and-observability,Shell 业务工具见 tool-and-automation-platform/shell-process-and-worktree。 关键词:SessionRuntimeResidency, TaskRunScheduler, ConcurrencyScheduler, ProviderRequestAdmissionScheduler, BrowserProcessPool, BoundedSerialEgress, GracefulShutdown。

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Git worktrees and Observability. The repository describes itself as: AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers. The licence is MIT.

When your agent uses it

  • Tasks that involve Git worktrees
  • Tasks that involve Observability

Example prompts

  • “/knowledge-capacity-lifecycle-and-egress”

What it can do on your machine

Read from SKILL.md and the folder at commit 30f8684. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Knowledge Capacity Lifecycle And Egress loads about 2.4k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 653 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from echoVic/blade-code at commit 30f8684, republished under its MIT licence (© echoVic). 653 words, ~2,378 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-capacity-lifecycle-and-egress/SKILL.md (or your agent's skills folder).
name
knowledge-capacity-lifecycle-and-egress
description
覆盖 Session、Task、Tool、Provider、Browser 的有界准入,跨 Session 公平性,SSE/ACP/Headless 输出背压,以及取消、关闭和进程树回收。 使用时机:排查 429/resource_exhausted、队列饥饿、内存增长、输出乱序、Session 驱逐、Browser 容量、关闭挂起或孤儿进程。 不包含:Provider 重试/熔断算法见 model-and-provider-runtime/provider-resilience-admission-and-observability,Shell 业务工具见 tool-and-automation-platform/shell-process-and-worktree。 关键词:SessionRuntimeResidency, TaskRunScheduler, ConcurrencyScheduler, ProviderRequestAdmissionScheduler, BrowserProcessPool, BoundedSerialEgress, GracefulShutdown。

Module Structure

该横切域用不同粒度的 reservation、permit、lease 和串行 egress 控制有限资源;每层都拥有独立队列、失败类型和释放责任,不能用一个全局 semaphore 替代。

Directory Layout
  • packages/cli/src/agent/runtime/SessionRuntimeResidency.ts — Web/ACP Runtime 驻留、pin、LRU 和 reservation
  • packages/cli/src/agent/runtime/TaskRunScheduler.ts — 顶层 Task active/pending count 与 retained bytes
  • packages/cli/src/tools/execution/ConcurrencyScheduler.ts — 进程和 Session 两级工具公平准入
  • packages/cli/src/tools/execution/ToolConcurrencyGate.ts — 单 executor 的 shared/exclusive FIFO 屏障
  • packages/cli/src/services/pi/providerRequestAdmission.ts — Provider domain/owner/class 加权准入
  • packages/cli/src/browser/BrowserOperationGate.ts — 单 Session Browser 操作串行化
  • packages/cli/src/browser/BrowserProcessPool.ts — 共享 Chromium 与隔离 Context lease
  • packages/cli/src/utils/BoundedSerialEgress.ts — 通用有界单写者输出
  • packages/cli/src/server/OrderedSseEgress.ts — replay/live 交接和 committed seq 顺序
  • packages/cli/src/services/GracefulShutdown.ts — 信号、清理栈、Hook 和日志关闭
  • packages/cli/src/utils/process/ — owned process tree、admission gate 和 PID identity
Decision Entry
  • SessionRuntimeResidency.reserve() — 初始化前预留 Runtime 容量
  • TaskRunScheduler.admit() — 顶层任务立即运行或进入 FIFO 队列
  • ConcurrencyScheduler.schedule() — 按 Session round-robin 获取工具 permit
  • ProviderRequestAdmissionScheduler.admit() — 按 failure domain、root owner 和 request class 准入
  • BrowserOperationGate.run() / BrowserProcessPool.acquire() — 页面操作与 Chromium Context 两级容量
  • BoundedSerialEgress.offer() — 在保留输出前同步判定 item/byte 上限
  • GracefulShutdownManager.shutdown() — 取消活动命令并有界执行清理

Branching Table

资源有容量时等待或可回收时满载、失败或关闭时
Session Runtimereservation 计数后初始化并 commit leaseWeb 可驱逐 idle、unpinned、canEvict 的 LRU residentACP 不驱逐;无候选返回可重试 resident_runtimes
顶层 Taskactive slot 空闲则立即运行且不计 pending bytespaused 或 active 满时按 FIFO 计 pending count/bytes任一 pending 上限命中即在执行前拒绝
工具进程级准入同时满足 global/session total 与 kind 限额后执行每个 Session 只取队首,跨 Session round-robinqueue full 或 180 秒等待超时返回 tool_busy
工具批内 gate连续 shared 调用并发exclusive 调用作为 FIFO 屏障pending 超 64 或 close 时取消未启动调用
Provider stream未配置并发旋钮时直接请求;配置后取得 physical-attempt permitforeground 优先、owner round-robin,background/internal 可 agingcount/bytes/full/timeout 返回脱敏可重试错误
Browser进程池复用一个 Chromium,每 Session 独立 Context,操作严格 FIFO最后一个 Context release 时关闭 ChromiumContext 或操作队列满分别返回 browser_capacity / browser_busy
Surface egress单 writer 按接纳顺序输出flush() 只等待调用时已接纳的 high-water markoverflow、oversized、write failure/timeout 关闭整条通道
进程关闭cleanup handlers 按注册逆序等待单项失败继续执行其余 cleanup4 秒 cleanup budget 后报错,5 秒 hard timeout 强制退出

Affected Scope

  • packages/cli/src/server/routes/session.ts — Web Runtime 驻留、Task 429 映射和 Session SSE
  • packages/cli/src/acp/BladeAgent.ts 与 packages/cli/src/acp/Session.ts — ACP 不驱逐驻留和有界 update egress
  • packages/cli/src/commands/headless.ts 与 packages/cli/src/commands/HeadlessOutputEgress.ts — Headless 信号传播和 stdout/stderr 背压
  • packages/cli/src/tools/execution/ToolExecutor.ts — 工具批内 gate、进程 permit 和 owner dispose
  • packages/cli/src/services/PiAIChatService.ts — 每次 physical Provider attempt 的准入与释放
  • packages/cli/src/browser/SessionBrowserRuntime.ts — Session 页面操作、Context lease 和 dispose
  • packages/cli/src/context/storage/ — 前台命令 lease、孤儿恢复和 durable process sidecar
  • packages/cli/src/hooks/SecureProcessExecutor.ts 与 packages/cli/src/lsp/LspClient.ts — 共用 owned process tree
  • packages/cli/web/src/store/session/ — 容量事件、队列位置和流状态投影

Gotchas

  • Session Runtime 的未完成 reservation 也占硬上限,避免并发初始化在 commit 前穿透容量;所有创建失败路径都必须调用 cancel() (packages/cli/src/agent/runtime/SessionRuntimeResidency.ts)
  • Web 只能驱逐 idle、未 pin、canEvict() 为真的 Runtime;ACP resident 永不隐式驱逐,客户端必须显式 session/close (packages/cli/src/agent/runtime/SessionRuntimeResidency.ts, docs/configuration/config-system.md)
  • 被驱逐 Runtime 的 dispose() 失败时会恢复为 poisoned resident;它仍占容量但不可 acquire 或再次驱逐,防止把未确认清理的资源当作空位 (packages/cli/src/agent/runtime/SessionRuntimeResidency.ts)
  • Task 和 Provider 的 byte budget 只约束等待队列;单个超过 pending budget 的请求在 active slot 空闲时仍可立即运行,但一旦需要排队就会被拒绝 (packages/cli/src/agent/runtime/TaskRunScheduler.ts, packages/cli/src/services/pi/providerRequestAdmission.ts)
  • TaskRunScheduler.configure() 冻结进程级限制,单个 Session 的 admission options 不能把它降成项目私有值;project 配置不得覆盖进程容量 (packages/cli/src/agent/runtime/TaskRunScheduler.ts)
  • 工具有两层独立顺序:ToolConcurrencyGate 保证同批 shared/exclusive 屏障,ConcurrencyScheduler 再限制进程/Session total 与 kind;删除任一层都会改变读写顺序或跨 Session 公平性 (packages/cli/src/tools/execution/ToolConcurrencyGate.ts, packages/cli/src/tools/execution/ConcurrencyScheduler.ts)
  • 工具 validation、worktree 隔离、Hook、权限和人工审批发生在 scarce permit 前;把审批移到 scheduler 内会让等待用户的调用长期占用执行容量 (packages/cli/src/tools/execution/ToolExecutor.ts, docs/reference/tool-concurrency.md)
  • Provider admission 默认关闭,只有配置 domain/global/owner 任一并发旋钮才启用;不能把 scheduler 常量误当成未配置时的隐藏吞吐限制 (packages/cli/src/services/PiAIChatService.ts, docs/reference/model-transport-recovery.md)
  • Provider permit 只覆盖一次真实 stream iterator,必须在 error、EOF 或 consumer return 后释放,再进行 retry backoff、circuit wait 或 fallback;跨重试持有 permit 会造成自锁和饥饿 (packages/cli/src/services/PiAIChatService.ts)
  • Provider 队列先按 foreground/background/internal 排序,再按 root owner round-robin;aging 会提升长期等待的 internal 请求,但不会改变其 pending class 计费 (packages/cli/src/services/pi/providerRequestAdmission.ts)
  • Browser 操作 gate 是单 Session 严格 FIFO,不区分只读与写;关闭会中止 active operation 并拒绝全部 queued operation,调用方必须等待 close() 返回再释放 Context (packages/cli/src/browser/BrowserOperationGate.ts)
  • BrowserProcessPool 的 launch failure 不缓存,意外断连会递增 generation 并使所有现有 lease 失效;旧 lease 的迟到 release 不得关闭新一代 Browser (packages/cli/src/browser/BrowserProcessPool.ts)
  • BoundedSerialEgress 任一 admission overflow 会关闭整条 transport,并拒绝已经接纳但尚未完成的项;它不是“只丢弃最新消息”的 ring buffer (packages/cli/src/utils/BoundedSerialEgress.ts)
  • SSE replay 期间会丢弃 buffered ephemeral 事件、按 seq 排序 committed 事件并去重;live committed seq 回退则立即关闭订阅 (packages/cli/src/server/OrderedSseEgress.ts)
  • POSIX 进程树必须以 detached group leader 启动;leader 已退出不代表 PGID 已结束,回收孤儿时还要在 SIGKILL 前重新校验 PID identity,防止杀死复用 PID (packages/cli/src/utils/process/OwnedProcessTree.ts, packages/cli/src/utils/process/ProcessIdentity.ts, git:fb8d6121)
  • Graceful shutdown 先 abort 活动 command,再逆序执行 cleanup,随后执行 SessionEnd Hook 和 logger shutdown;cleanup handler 不应自行 process.exit() 截断后续回收 (packages/cli/src/services/GracefulShutdown.ts)
Show full SKILL.md (155 more words)Show less

Architecture

  • Runtime、Task、Tool、Provider 和 Browser 各自拥有与故障域匹配的准入器:Session 用 reservation/lease,Task/Provider 用 ticket/permit,工具另加批内 barrier,Browser 另加 Context pool (packages/cli/src/agent/runtime/SessionRuntimeResidency.ts, packages/cli/src/services/pi/providerRequestAdmission.ts)
  • 进程级公平调度以 Session 或 root owner 为轮转单位,局部受阻的队首不会阻塞其他 eligible owner;取消和释放都会立即重新 drain (packages/cli/src/tools/execution/ConcurrencyScheduler.ts, packages/cli/src/services/pi/providerRequestAdmission.ts)
  • Surface egress 将内存上限、单 writer、写超时和关闭传播集中在通用队列,SSE、ACP 与 Headless 只负责各自的编码和 replay 语义 (packages/cli/src/utils/BoundedSerialEgress.ts, packages/cli/src/server/OrderedSseEgress.ts)

Decisions

  • 输出背压采用断开慢消费者而不是丢事件,因为 committed 事件顺序和完整性高于维持单个慢连接;其他订阅者不受影响 (packages/cli/src/server/OrderedSseEgress.ts, git:1af43232)
  • 工具并发同时保留 process total、Session total 和 kind 上限,避免一个 Session 或大量 readonly 调用挤占全部 execute/write 容量 (packages/cli/src/tools/execution/ConcurrencyScheduler.ts, git:527cb02b)
  • Provider 准入使用 failure-domain 与 root-owner 双重隔离,并给 foreground 保留容量;这是为了让后台子任务和内部采样不能放大上游故障 (packages/cli/src/services/pi/providerRequestAdmission.ts, git:852c8cba, git:471f90f0)

Branching Behavior

  • Session Runtime 容量满时,Web reservation 可先回收最旧 eligible resident;ACP reservation 直接返回 typed capacity error,不改变任何已有 Session (packages/cli/src/agent/runtime/SessionRuntimeResidency.ts)
  • Task scheduler paused 时即使有 active slot 也排队;resume 或提高并发限制会按 FIFO drain,降低 byte limit 不会驱逐已经接受的等待项 (packages/cli/src/agent/runtime/TaskRunScheduler.ts)
  • Tool shared 调用只在队首连续 shared 区间并发;遇到 exclusive 后,后续 shared 不能越过该屏障 (packages/cli/src/tools/execution/ToolConcurrencyGate.ts)
  • Provider foreground 排在较新的 background/internal 前,但每 30 秒 aging 一级,长期 internal 最终可提升到 foreground rank (packages/cli/src/services/pi/providerRequestAdmission.ts)
  • SSE fresh 连接按 callback 到达顺序释放初始化缓冲,带 replay 的连接改按 committed seq 排序且只发送高于 replay 水位的事件 (packages/cli/src/server/OrderedSseEgress.ts)
  • Browser Context 数量达到上限时拒绝新 Session,不会抢占已有 Context;同一 Context 内的页面操作则进入有界串行队列 (packages/cli/src/browser/BrowserProcessPool.ts, packages/cli/src/browser/BrowserOperationGate.ts)
  • 进程自然退出会释放 OwnedProcessTree 所有权;durable admission gate 则可设置 releaseOnExit: false,直到独立确认整个进程组已清理才释放 (packages/cli/src/utils/process/CommandAdmissionGate.ts, packages/cli/src/utils/process/OwnedProcessTree.ts)

© echoVic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .trae/knowledges/workspace-policy-and-shared-foundations/capacity-lifecycle-and-egress of echoVic/blade-code.

Open the folder on GitHubat commit 30f8684

Compare with similar skills

Knowledge Capacity Lifecycle And Egress next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Knowledge Capacity Lifecycle And Egress compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Capacity Lifecycle And Egress this skillechoVic/blade-code181—~2.4kAutomated safety check: PassMIT
Vercel Optimize Auditvercel-labs/agent-skills32k8 repos~4.3kAutomated safety check: PassNone
Kubeshark Installerkubeshark/kubeshark12k—~3.6kAutomated safety check: NotesApache-2.0
Kubeshark KFL2 Filter Referencekubeshark/kubeshark12k—~3.6kAutomated safety check: PassApache-2.0
KubeSphere ServiceMesh Managerkubesphere/kubesphere17k—~2.4kAutomated safety check: PassCustom licence
Kubernetes Network Root Cause Analysiskubeshark/kubeshark12k—~5.3kAutomated safety check: PassApache-2.0

Similar skills

  • Vercel Optimize Audit

    vercel-labs/agent-skills

    Official

    Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.

    32k GitHub starsUsed in 8 repos~4.3k tokens
    DevOps & CloudAuto-check passed
  • Kubeshark Installer

    kubeshark/kubeshark

    Installs and configures Kubeshark on a Kubernetes cluster, choosing between the quick CLI path and a Helm install with custom values.

    12k GitHub stars~3.6k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Syntax reference for KFL2, the CEL-based display filter language used to search Kubernetes network traffic captured by Kubeshark, loaded before any filter is written.

    12k GitHub stars~3.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • KubeSphere ServiceMesh Manager

    kubesphere/kubesphere

    Installs, checks and troubleshoots the KubeSphere ServiceMesh extension (Istio, Kiali, Jaeger), including grayscale release, sidecar injection, topology and tracing issues.

    17k GitHub stars~2.4k tokensUpdated 2 mo ago
    DevOps & CloudAuto-check passed
  • Investigates past Kubernetes incidents from Kubeshark traffic snapshots: takes captures, dissects API calls, extracts PCAPs and compares traffic over time.

    12k GitHub stars~5.3k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Caveman Gateway Setup

    JuliusBrussee/caveman

    Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

    111k GitHub starsUsed in 1 repo~2.6k tokens
    DevOps & CloudAuto-check: warnings

More from echoVic/blade-code

All 38 skills in this repo
  • Base64 Parser

    echoVic/blade-code

    Base64 编解码工具,支持编码/解码文本、JSON、二进制文件,自动检测格式,支持批量处理. An agent skill from echoVic/blade-code.

    181 GitHub stars~545 tokensUpdated 12 days ago
    Auto-check: notes
  • Code Review

    echoVic/blade-code

    Review frontend code for best practices, bugs, and improvements.

    181 GitHub stars~377 tokensUpdated 12 days ago
    Auto-check: notes
  • GitHub Explorer

    echoVic/blade-code

    Explore and summarize popular GitHub projects. An agent skill from echoVic/blade-code.

    181 GitHub stars~434 tokensUpdated 12 days ago
    Auto-check passed
  • 覆盖 Session 级 LSP 配置快照、stdio 进程、文档同步、语义查询、诊断回注、崩溃恢复 和子 Session 继承。进入条件:新增语言服务器、修改 LSP 工具、排查诊断缺失/重复、 处理 worktree 或 ACP 差异、修复进程泄漏或 transport 代际问题。不包含:VS Code 扩展桥接(见…

    181 GitHub stars~1.9k tokensUpdated 12 days ago
    Auto-check passed
  • 覆盖 SkillRegistry、SKILL.md 延迟加载、自定义命令 Markdown 解析、来源覆盖、插件 命名空间、Session 快照和模型/用户调用入口。进入条件:新增 Skill 或命令字段、调整 发现优先级、调试 /command 或 Skill 工具、修改 Prompt 元数据或消费者集成。不包含: 插件安装生命周期(见…

    181 GitHub stars~2.1k tokensUpdated 12 days ago
    Auto-check passed
  • Covers 领域能力如何包装成内置工具、getBuiltinTools 的 Session 依赖注入、ToolSearch 延迟激活,以及 Goal/Task/Team/Plan/Skill/LSP/MCP/Web/Config/Worktree 适配边界。

    181 GitHub stars~2.1k tokensUpdated 12 days ago
    Auto-check passed

Categories

Questions about Knowledge Capacity Lifecycle And Egress

What does Knowledge Capacity Lifecycle And Egress do?

覆盖 Session、Task、Tool、Provider、Browser 的有界准入,跨 Session 公平性,SSE/ACP/Headless 输出背压,以及取消、关闭和进程树回收。. Knowledge Capacity Lifecycle And Egress is an agent skill from echoVic/blade-code.

When should I use Knowledge Capacity Lifecycle And Egress?

Knowledge Capacity Lifecycle And Egress fits situations like: tasks that involve Git worktrees; tasks that involve Observability.

How do I install Knowledge Capacity Lifecycle And Egress in Claude Code?

Run `npx skills add echoVic/blade-code --skill knowledge-capacity-lifecycle-and-egress -a claude-code`. Or copy the skill folder (.trae/knowledges/workspace-policy-and-shared-foundations/capacity-lifecycle-and-egress in echoVic/blade-code) into .claude/skills/knowledge-capacity-lifecycle-and-egress in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Capacity Lifecycle And Egress in Codex?

Run `npx skills add echoVic/blade-code --skill knowledge-capacity-lifecycle-and-egress -a codex`. Or copy the skill folder (.trae/knowledges/workspace-policy-and-shared-foundations/capacity-lifecycle-and-egress in echoVic/blade-code) into .agents/skills/knowledge-capacity-lifecycle-and-egress in your project. Codex loads it when a task matches its description.

Can I use Knowledge Capacity Lifecycle And Egress in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add echoVic/blade-code --skill knowledge-capacity-lifecycle-and-egress -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-capacity-lifecycle-and-egress, .gemini/skills/knowledge-capacity-lifecycle-and-egress, .github/skills/knowledge-capacity-lifecycle-and-egress and .opencode/skills/knowledge-capacity-lifecycle-and-egress in your project.

What does Knowledge Capacity Lifecycle And Egress need to run?

SKILL.md names no scripts, command-line tools or credentials: Knowledge Capacity Lifecycle And Egress is instructions for the agent only.

Does Knowledge Capacity Lifecycle And Egress access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Knowledge Capacity Lifecycle And Egress safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Knowledge Capacity Lifecycle And Egress use?

Knowledge Capacity Lifecycle And Egress is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Knowledge Capacity Lifecycle And Egress use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Knowledge Capacity Lifecycle And Egress?

Skills that share tags, products or a category with Knowledge Capacity Lifecycle And Egress: Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars), Kubeshark Installer (kubeshark/kubeshark, 12k stars), Kubeshark KFL2 Filter Reference (kubeshark/kubeshark, 12k stars) and KubeSphere ServiceMesh Manager (kubesphere/kubesphere, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Capacity Lifecycle And Egress?

echoVic (a GitHub user) maintains it in echoVic/blade-code, which has 181 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on September 27, 2026.

Source: echoVic/blade-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.