Agent skill

Host Instruction Projection

by devcodex-labs in devcodex-labs/devcodex

宿主指令投影 Owner — 从统一 instructions 真相源确定性生成精简 Host Kernel、薄包装、覆盖回执与完整回退

AGPL-3.0Auto-check passed

Install Host Instruction Projection

skills CLI
$ npx skills add devcodex-labs/devcodex --skill host-instruction-projection -a claude-code

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

GitHub CLI
$ gh skill install devcodex-labs/devcodex host-instruction-projection --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/devcodex-labs/devcodex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content/skills/host-instruction-projection .claude/skills/host-instruction-projection && 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
host-instruction-projection
GitHub stars
439
Token cost
~2.2k tokens
SKILL.md length
754 words
Files
2
Skills in repo
70
Repo updated
First seen
Licence
AGPL-3.0

At a glance

宿主指令投影 Owner — 从统一 instructions 真相源确定性生成精简 Host Kernel、薄包装、覆盖回执与完整回退

  • Works in 4 steps: 官方能力证据必须覆盖 plugin… → UserPromptSubmit / Stop / PreCompact 只允许… → plain grok 必须从 workspace root 与 child… → …
  • SKILL.md covers 职责, 触发条件, HostInstructionProjectionGate and KernelBudgetGate, plus 10 more sections
  • Calls node, claude and codex

What it does

Host Instruction Projection is an agent skill from devcodex-labs/devcodex. 宿主指令投影 Owner — 从统一 instructions 真相源确定性生成精简 Host Kernel、薄包装、覆盖回执与完整回退

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `intent.json`).

The repository describes itself as: Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts. The licence is AGPL-3.0.

Example prompts

  • “/host-instruction-projection”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 官方能力证据必须覆盖 plugin install/update/uninstall、[plugins].enabled、plugin hooks 的 GROK_PLUGIN_ROOT、passive Hook stdout ignored、官方 --rules 与 grok…
  2. UserPromptSubmit / Stop / PreCompact 只允许 passive 观测或运行态维护;PreToolUse 才能按 Grok 顶层 {decision, reason} 契约形成阻断。任何 passive stdout 都不能作为 kernel…
  3. plain grok 必须从 workspace root 与 child project 两个 cwd direct 验证 plugin identity,并分别记录 root native kernel 与 child Skill-discovery 上限;工作区外必须…
  4. devcodex grok launcher 必须先按官方 --cwd 解析最终 cwd/owner,在 workspace root 校验原生 kernel 存在,并仅在子 Git 项目追加同一 kernel;合并用户额外 --rules,拒绝 system prompt…

What it can do on your machine

Read from SKILL.md and the folder at commit 1dd4525. 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

    Shell commands in SKILL.md call:

    • node
    • claude
    • codex
    • gemini
    • cursor

    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

Host Instruction Projection loads about 2.2k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 754 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 devcodex-labs/devcodex at commit 1dd4525, republished under its AGPL-3.0 licence (© devcodex-labs). 754 words, ~2,164 tokens.

Download SKILL.mdSave it as .claude/skills/host-instruction-projection/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
host-instruction-projection
description
宿主指令投影 Owner — 从统一 instructions 真相源确定性生成精简 Host Kernel、薄包装、覆盖回执与完整回退

Host Instruction Projection Skill

职责

当任务涉及 always-on instructions 体积、Copilot/Codex/Claude/Gemini/Grok 规则加载、宿主入口文件、生成式规则投影、重复指令碰撞或完整规范回退时,本 Skill 是唯一 Owner。

本 Skill 只负责 instructions.md → projection config → generated host projections → coverage receipt → deployment descriptors。它不替代 intent、cp-gate、load-profile、spec-governance 或 host-contract-verification 的执行正文,也不把派生文件升级成第二规范真相源。

确定性实现位于 scripts/lib/host-instruction-projection.js,生成配置位于 scripts/host-instruction-projection.json,派生产物位于 host-projections/。

触发条件

场景是否触发
修改 instructions.md 中 S/C、路由、CP、Context、治理或闭环语义必须
修改宿主入口文件、安装路径或 deployment descriptor必须
新增/调整 Copilot、Claude、Codex、Gemini、Grok、Cursor surface必须
调整 always-on 指令预算或 full fallback必须
仅修改按需 Skill 正文且不触达投影锚点N/A + skipReason

HostInstructionProjectionGate

投影链固定为:

instructions.md → mandatory rule parser → semantic replay groups → HostKernelV1 → thin wrappers → HostInstructionCoverageReceiptV1。

  • instructions.md 是唯一规范真相源;配置只声明抽取规则、语义锚点、宿主包装与预算。
  • S01S07、C01C22 必须逐 ID 解析并进入 kernel;缺号、重复号、源锚点缺失或投影锚点缺失均 fail closed。
  • 语义组至少覆盖 routing、CP、Context、governance、closure;用户可见输出与 auto 边界作为横切组进入同一回放。
  • coverage 必须为 100%;生成器、--check、负向 mutation 和 staged/post-commit freshness 缺一不可。
  • 禁止手工编辑 host-projections/*;发现漂移时重新生成,不能在派生文件上补规则。

KernelBudgetGate

产物预算
shared/Copilot kernel≤ 16 KiB 且 ≤ 200 行
Claude/Gemini wrapper≤ 2 KiB
相同完整 kernel 重复入口0

预算超限、覆盖不完整或碰撞时,投影状态必须为 full-fallback,不得把部分 kernel 标成可用。性能优化不能降低安全、CP、恢复、治理或 ECR 语义。

HostSurfaceProjectionGate

Surfacealways-on按需/回退
Copilot.github/copilot-instructions.md(Copilot projection).github/skills + .agents/devcodex/instructions.full.md
CodexAGENTS.md(shared kernel).agents/skills + .agents/devcodex/instructions.full.md
ClaudeCLAUDE.md(仅导入 @AGENTS.md 的薄包装).claude/skills + full fallback
GeminiGEMINI.md(导入 @AGENTS.md 的薄包装).agents/skills + full fallback
Grok独立 project-portable 安装使用原生 AGENTS.md;workspace 根原生读取共享 kernel;workspace 子 Git 项目用 devcodex grok 官方 --rules launcher 绑定同一 kernelworkspace 插件提供 resolver Skill、Hook/MCP bridge;官方用户级本地插件登记绑定 workspace source owner,配置只维护 enabled 状态

wrapper 只允许宿主能力提示和 shared kernel 指针;不得复制完整规则。Grok 不创建 .grok/rules 规范副本。

HostAdapterScopeGate

每次生成、安装、更新、状态检查、诊断或卸载宿主 adapter 前必须先形成 HostAdapterScopeV1:

scopeowner / activation子项目默认产物
workspace-nativeworkspace root / ancestor 或宿主原生工作区发现0
user-registered-workspaceworkspace root / 官方用户级本地插件登记 + 配置 enabled 状态0
project-portable显式 project root / repo-shared project discovery按显式选择生成
  • workspace-namespace 默认只能选择前两类;不能因为某宿主从 repo cwd 启动,就把 ignored adapter 复制进每个子项目。
  • Grok 的 workspace owner 固定为非自动发现 source <workspace-root>/.grok/devcodex/plugins/devcodex-workspace,只由官方 user installation 暴露一个插件 identity;旧 .grok/plugins/devcodex-workspace 仅作可逆迁移输入。插件只含 metadata、thin resolver、Hook/MCP bridge;不得复制完整 kernel 或 Skill 树。
  • 使用 Grok 官方 plugin install/update/uninstall 管理用户级本地插件登记,登记的 source_path 必须指回 workspace owner,安装副本 digest 必须一致;官方命令导致的配置格式化必须恢复为调用前原始字节。
  • 用户配置只增量维护 DevCodex plugin enabled 项,并移除同一 workspace owner 的旧受管 path 项以避免同名插件碰撞;未知键、注释和其他插件必须保留,重复执行幂等,移除时只触达完全匹配的受管项。用户显式 disabled 时 fail closed。
  • 插件必须把 cwd 解析出的 workspace 与自身 owner workspace 比对;工作区外 no-op,根缺失/歧义 fail closed,不得全局注入项目状态。
  • Grok 官方契约规定 passive Hook stdout 被忽略,因此 UserPromptSubmit 不得声明或模拟上下文注入。工作区根依赖原生 AGENTS.md;子 Git 项目需要 full 证据时使用 devcodex grok,由官方 --rules 绑定同一 kernel。plain child 仅可保持 Skill-discovery / partial 口径。
  • project-portable 必须由显式参数选择,其产物应是可共享、manifest 管理的项目能力;不能靠 .gitignore 隐藏。
  • 同一规范化 destination 当前 owner 只能为 1。workspace 模式下 project manifest 的 legacy host claims 必须退休,workspace manifest 的 missing/mismatch/stale/duplicate 必须为 0。
  • 旧项目 adapter 只能在新链路验证后做可逆 quarantine;不得由 update 静默永久删除用户文件。
  • uninstall --host grok 只移除官方用户安装与精确受管 config 项,必须保留 workspace plugin source、未知配置和其他插件;重复卸载幂等。portable 项目资产不得借此静默删除。

GrokWorkspacePluginGate

  1. 官方能力证据必须覆盖 plugin install/update/uninstall、[plugins].enabled、plugin hooks 的 GROK_PLUGIN_ROOT、passive Hook stdout ignored、官方 --rules 与 grok inspect --json;变更前重新核验时效性。
  2. UserPromptSubmit / Stop / PreCompact 只允许 passive 观测或运行态维护;PreToolUse 才能按 Grok 顶层 {decision, reason} 契约形成阻断。任何 passive stdout 都不能作为 kernel evidence。
  3. plain grok 必须从 workspace root 与 child project 两个 cwd direct 验证 plugin identity,并分别记录 root native kernel 与 child Skill-discovery 上限;工作区外必须 no-op。
  4. devcodex grok launcher 必须先按官方 --cwd 解析最终 cwd/owner,在 workspace root 校验原生 kernel 存在,并仅在子 Git 项目追加同一 kernel;合并用户额外 --rules,拒绝 system prompt override 与重复 cwd 冲突,并以 headless direct replay 证明 launcher-rules。不得用 launcher 结果升级 plain child 结论,也不得从父 workspace 借用缺失的子 workspace kernel。

FullFallbackGate

完整源固定部署到 .agents/devcodex/instructions.full.md,且不位于任一宿主自动规则目录。以下任一情况必须使用或建议读取 full fallback:

  • coverage、source/config digest 或生成新鲜度失败;
  • 当前任务属于 audit/migration,或低置信无法安全裁剪;
  • kernel 中的 Owner 索引要求读取按需 Skill,但 Skill 缺失/不可读;
  • 宿主报告 0 instruction、root 截断、冲突版本或未知 import 语义。

full fallback 是兼容/故障路径,不得与 kernel 同时作为两个 always-on 完整副本加载。

Show full SKILL.md (287 more words)Show less

GrokFullLaunchAndPrivateTempGate

  • devcodex grok 的 SkillRoute bootstrap 必须明确 active,才允许物化 GrokPrivateTempOwnerV1 prompt snapshot 并 spawn child;bootstrap error/inactive 分别返回 GROK_FULL_BOOTSTRAP_ERROR / GROK_FULL_BOOTSTRAP_INACTIVE,且 promptMaterialized=0、spawnCount=0。plain Grok 继续保持 Partial,不能用 SessionStart fallback 冒充 Full bootstrap。
  • launcher 的 prompt snapshot 与 plugin SessionStart 分属两个 writer,只共享 grok/plugins/devcodex-workspace/lib/private-temp-contract.cjs 的 schema/identity/path guard;installed plugin 不得反向 require source-only 文件,诊断 owner record 不保存 prompt body。
  • SessionStart 每次创建 GrokSessionPrivateOwnerV1 nonce owner root;sessionId 缺失也必须保持唯一。owner token、host/PID、path containment、TTL 与 state 任一不可验证都 fail closed;仅 expired + dead owner 可进入恢复,live/unknown owner 不得抢占或清理。

HostInstructionCollisionGate

碰撞检查至少记录:path / surface / role / digest / bytes / lines / sourceDigest / cwd / projectRoot。

  • 同一路径多 writer、相同完整内容多入口、不同 sourceDigest kernel、wrapper 未指向 shared kernel、入口为 0 字节或超预算均为 blocker。
  • import-only wrapper 计入实际 bytes,但不按第二份完整 kernel 计数。
  • init --host 遇到未授权的现有冲突入口时返回 HOST_INSTRUCTION_COLLISION;update --host 通过显式 force 路线更新。
  • direct host inspect 不可用时最高为 instruction-backed/unverified,不得凭 fixture 升级 enforced。

CLI 与部署消费者

  • 公共选择器:--host <copilot|claude|codex|gemini|grok|cursor|all>。
  • 旧 --claude、--codex 保留;--gemini、--grok、--cursor 为等价 alias。
  • GlobalOnlyWorkspaceCleanModeV1 下,bare init/update 只维护 .devcodex,不部署任何 workspace 宿主 adapter;用户级 global-adapters apply 默认部署六宿主。legacy project projection 仍只有 copilot+claude+codex+gemini+grok 五类工作区 surface,Cursor 必须保持零业务 workspace .cursor 产物。
  • 重复或冲突 selector 使用 CLI_HOST_SELECTION_CONFLICT;未知 host 使用 CLI_HOST_UNSUPPORTED。
  • managed manifest 必须记录 projection source/content digest,并保证规范化物理 destination 单一 current owner;dry-run 零写入;从 source cwd 与目标项目 cwd 分别验证边界。
  • workspace-namespace 从 child project 调用默认、单宿主或 --host all install/update 时,所有非 portable target/manifest owner 必须解析为 workspace root;Grok uninstall 与 status/doctor 也消费相同 scope identity。uninstall 不删除 workspace source。

验证路线

  1. node scripts/generate-host-instruction-projections.js --check。
  2. node scripts/test-host-instruction-projection.js:规则缺失、锚点 mutation、预算回退、重复内容碰撞、派生新鲜度。
  3. node scripts/test-host-adapters.js:Gemini/Grok/Cursor event 与输出映射。
  4. node scripts/test-cli-command-registry.js 与 host install fixture:默认兼容、六 host、aliases、unknown/conflict、dry-run、collision、two-cwd、Cursor workspace 零产物,以及 Grok uninstall/repeat/reinstall 配置保真。
  5. grok plugin validate grok/plugins/devcodex-workspace + workspace/project/outside grok inspect --json;无 direct 的宿主保持 UNVERIFIED。
  6. node scripts/run-validation.js --route full --no-cache、package/Profile/deploy、staged freshness 与 post-commit clean replay。

回滚

任一 correctness、coverage、碰撞或 direct evidence 失败:

  1. 将投影状态降为 full-fallback;
  2. 保留旧 CLI aliases 与完整 instructions.md reader;
  3. 按 surface 回滚 adapter,不删除其他宿主已通过的派生物;
  4. 记录 source/config digest、失败探针和恢复条件,修复后重新生成并完整回放。

禁止事项

  • 手工维护六份完整规范。
  • 用关键词计数代替 S/C ID 与语义锚点回放。
  • 为压缩体积删除安全、CP、Context、治理、恢复或 ECR 不变量。
  • 在缺少 direct evidence 时宣称宿主已实际加载、执行或强制。
  • 把 coverage receipt 或生成 header 当成规范真相源。
  • 在 workspace 默认模式向子项目生成 AGENTS.md/.grok/.codex/.claude/.gemini,或让读写/诊断使用不同作用域解析器。

© devcodex-labs, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in content/skills/host-instruction-projection of devcodex-labs/devcodex.

  • SKILL.md
  • intent.json

Open the folder on GitHubat commit 1dd4525

Compare with similar skills

Host Instruction Projection 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.

Host Instruction Projection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Host Instruction Projection this skilldevcodex-labs/devcodex439—~2.2kAutomated safety check: PassAGPL-3.0
Projects Work Managementsickn33/agentic-awesome-skills47k1 repos~4.1kAutomated safety check: PassMIT
Acreadiness Generate Instructionsgithub/awesome-copilot40k1 repos~2.1kAutomated safety check: PassMIT
Copilot Instructions Blueprint Generatorgithub/awesome-copilot40k3 repos~3.7kAutomated safety check: PassMIT
Kernel Organizationsgl-project/sglang37k—~1.3kAutomated safety check: PassApache-2.0
Find Project Anomaliespenpot/penpot61k—~1.2kAutomated safety check: PassMPL-2.0

Similar skills

  • Projects Work Management

    sickn33/agentic-awesome-skills

    Project register: owner, team, priority, progress percentage, milestones, deliverables and budget against actual cost.

    47k GitHub starsUsed in 1 repo~4.1k tokens
    Product & Project ManagementAuto-check passed
  • Acreadiness Generate Instructions

    github/awesome-copilot

    Official

    Generate tailored AI agent instruction files via AgentRC instructions command.

    40k GitHub starsUsed in 1 repo~2.1k tokens
    DevelopmentAuto-check passed
  • Official

    Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns…

    40k GitHub starsUsed in 3 repos~3.7k tokens
    Agent WorkflowsAuto-check passed
  • Kernel Organization

    sgl-project/sglang

    Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations.

    37k GitHub stars~1.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Check a GitHub milestone against the Main project board, report the five anomaly types to tmp/<MILESTONE-ANOMALIES.md, and fix missing milestone assignments on request.

    61k GitHub stars~1.2k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Project Status Artifact

    anthropics/claude-plugins-official

    Official

    Builds and publishes a tabbed status page for a project with several workstreams, kept current by refreshing the same private page.

    37k GitHub stars~5.1k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from devcodex-labs/devcodex

All 70 skills in this repo
  • Accessibility I18n

    devcodex-labs/devcodex

    无障碍与国际化专家 Owner — 当任务涉及可访问性、键盘操作、焦点、屏幕阅读器、ARIA、语言地区、本地化、RTL、翻译资源、用户可见文案或多语言文档时使用;要求把包容性体验和本地化验证绑定到真实用户路径。

    439 GitHub stars~718 tokensUpdated 20 days ago
    Auto-check passed
  • AI Agent System Architecture

    devcodex-labs/devcodex

    AI Agent 系统架构专家 Owner — 当任务涉及 Agent 路由、工具调用、上下文管理、记忆、状态机、权限、人机协作、可观测性、回放验证或模型辅助治理时使用;要求把 Agent 行为设计成可解释、可恢复、可审计。

    439 GitHub stars~2.4k tokensUpdated 20 days ago
    Auto-check passed
  • API Contract Architecture

    devcodex-labs/devcodex

    API 契约架构专家 Owner — 当任务涉及 public API、HTTP/SDK/CLI 契约、版本兼容、错误模型、分页过滤、幂等、Schema、类型、迁移或消费者影响时使用;要求先冻结消费者契约,再设计实现与验证。

    439 GitHub stars~865 tokensUpdated 20 days ago
    Auto-check passed
  • Architecture Design

    devcodex-labs/devcodex

    架构设计文档编排 Owner — 当用户要求架构设计、系统设计、技术架构或可指导开发、Review 与任务拆分的完整方案时使用;要求从业务流程反推节点、状态、数据、一致性、异常补偿、ADR 与实施任务。

    439 GitHub stars~1.1k tokensUpdated 20 days ago
    Auto-check passed
  • Audit Common

    devcodex-labs/devcodex

    审查公共维度 G0~G5 + Profile Freshness Check — 所有 audit 子类型必先执行的基础维度层

    439 GitHub stars~4.1k tokensUpdated 20 days ago
    Auto-check passed
  • Audit Session

    devcodex-labs/devcodex

    审计工作流的跨会话状态机 — 在 <audit-root/.audit-state/<session-id.json 持久化轮次/发现项/收敛状态,支持 Token 中断后精准恢复

    439 GitHub stars~1.8k tokensUpdated 20 days ago
    Auto-check passed

Questions about Host Instruction Projection

What does Host Instruction Projection do?

宿主指令投影 Owner — 从统一 instructions 真相源确定性生成精简 Host Kernel、薄包装、覆盖回执与完整回退. Host Instruction Projection is an agent skill from devcodex-labs/devcodex.

How do I install Host Instruction Projection in Claude Code?

Run `npx skills add devcodex-labs/devcodex --skill host-instruction-projection -a claude-code`. Or copy the skill folder (content/skills/host-instruction-projection in devcodex-labs/devcodex) into .claude/skills/host-instruction-projection in your project. Claude Code loads it when a task matches its description.

How do I install Host Instruction Projection in Codex?

Run `npx skills add devcodex-labs/devcodex --skill host-instruction-projection -a codex`. Or copy the skill folder (content/skills/host-instruction-projection in devcodex-labs/devcodex) into .agents/skills/host-instruction-projection in your project. Codex loads it when a task matches its description.

Can I use Host Instruction Projection 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 devcodex-labs/devcodex --skill host-instruction-projection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/host-instruction-projection, .gemini/skills/host-instruction-projection, .github/skills/host-instruction-projection and .opencode/skills/host-instruction-projection in your project.

What does Host Instruction Projection need to run?

Going by SKILL.md and its folder, Host Instruction Projection needs the command-line tools its instructions call (node, claude, codex, gemini and cursor).

Does Host Instruction Projection 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 Host Instruction Projection 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 Host Instruction Projection use?

Host Instruction Projection is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Host Instruction Projection use?

About 2.2k tokens (SKILL.md is roughly 8.7k 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 Host Instruction Projection?

Skills that share tags, products or a category with Host Instruction Projection: Projects Work Management (sickn33/agentic-awesome-skills, 47k stars), Acreadiness Generate Instructions (github/awesome-copilot, 40k stars), Copilot Instructions Blueprint Generator (github/awesome-copilot, 40k stars) and Kernel Organization (sgl-project/sglang, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Host Instruction Projection?

devcodex-labs (a GitHub organization) maintains it in devcodex-labs/devcodex, which has 439 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on September 17, 2026.

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