MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Dispatch independent tasks to parallel workers or subagents without write collisions.
Install Agent Native
$ npx skills add boshu2/agentops --skill agent-native -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install boshu2/agentops agent-native --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/boshu2/agentops.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-native .claude/skills/agent-native && rm -rf skills-srcUse ~/.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/
Install the "agent-native" agent skill from https://github.com/boshu2/agentops/tree/main/skills/agent-native into .claude/skills/agent-native/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-native", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/boshu2/agentops/tree/main/skills/agent-nativeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add boshu2/agentops --skill agent-native -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install boshu2/agentops agent-native --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/boshu2/agentops.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-native .agents/skills/agent-native && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-native" agent skill from https://github.com/boshu2/agentops/tree/main/skills/agent-native into .agents/skills/agent-native/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-native", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add boshu2/agentops --skill agent-native -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install boshu2/agentops agent-native --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/boshu2/agentops.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-native .cursor/skills/agent-native && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-native" agent skill from https://github.com/boshu2/agentops/tree/main/skills/agent-native into .cursor/skills/agent-native/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-native", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/boshu2/agentops.git --path skills/agent-native--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add boshu2/agentops --skill agent-native -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install boshu2/agentops agent-native --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/boshu2/agentops.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-native .gemini/skills/agent-native && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-native" agent skill from https://github.com/boshu2/agentops/tree/main/skills/agent-native into .gemini/skills/agent-native/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-native", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install boshu2/agentops agent-nativeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add boshu2/agentops --skill agent-native -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/boshu2/agentops.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-native .github/skills/agent-native && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-native" agent skill from https://github.com/boshu2/agentops/tree/main/skills/agent-native into .github/skills/agent-native/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-native", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add boshu2/agentops --skill agent-native -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install boshu2/agentops agent-native --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/boshu2/agentops.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-native .opencode/skills/agent-native && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-native" agent skill from https://github.com/boshu2/agentops/tree/main/skills/agent-native into .opencode/skills/agent-native/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-native", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-native- GitHub stars
- 447
- Used in
- 1 other repo
- Token cost
- ~1.9k tokens
- SKILL.md length
- 848 words
- Files
- 9 (incl. scripts, references)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Dispatch independent tasks to parallel workers or subagents without write collisions.
- Works in 6 steps: Before starting a worker, require caller… → At startup, before substantive work,… → Keep concurrent writers disjoint and… → …
- Planning agents in parallel
- SKILL.md covers Before launch, and while running, Roles, Launch and observe and Adapters and judgment, plus 1 more section
- Runs Python scripts from its folder
What it does
Agent Native is an agent skill from boshu2/agentops. Dispatch independent tasks to parallel workers or subagents without write collisions. Use when: running or planning agents in parallel, even two; check scopes before any launch.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `references/RAW_SOURCE_READS.md`, `references/context-budget-delegation.md` and `references/judgment-receipts.md`).
It sits in Agent Workflows. The repository describes itself as: DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it. The licence is Apache-2.0.
When your agent uses it
- Planning agents in parallel
- Check scopes before any launch
Example prompts
- “/agent-native”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Before starting a worker, require caller intent, role, workspace, authorized
- At startup, before substantive work, capture the observed runtime, session
- Keep concurrent writers disjoint and isolated. Runtime coordination is not a
- Observe through native waits or status notifications; observation costs time
- For new authorized work after a worker completes, use the runtime's
- Record provider state, transcript references, artifacts and terminal status.
What it can do on your machine
Read from SKILL.md and the folder at commit 3bdbfed. 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
Ships 1 file in scripts/ (Python), which the agent can run.
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
Agent Native loads about 1.9k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 848 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from boshu2/agentops at commit 3bdbfed, republished under its Apache-2.0 licence (© boshu2). 848 words, ~1,935 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-native/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- agent-native
- description
- Dispatch independent tasks to parallel workers or subagents without write collisions. Use when: running or planning agents in parallel, even two; check scopes before any launch.
- practices
- team-topologies, design-by-contract
- hexagonal_role
- supporting
- consumes
- explicit-role-packets
- produces
- runtime-evidence, worker-handoff, per-packet-results
- skill_api_version
- 1
- user-invocable
- true
- metadata.tier
- meta
- metadata.capabilities
- role_dispatch, observe_workers, handoff, dispatch_once
- metadata.effects
- manage_runtime_sessions, invoke_selected_executor
- metadata.canonical_status
- canonical
Agent Native
Launch and observe caller-selected agent sessions as explicit roles, and return runtime facts per packet. Execution does not validate output, and the runtime never becomes AgentOps lifecycle authority: an adapter cannot select AgentOps semantics, issue a binding verdict, or turn factory completion into delivery or validation proof. Orchestrate decides what to dispatch and when; this skill launches and observes.
Before launch, and while running
- Validate the whole batch first. Every packet needs its selected executor, packet identity, all transitive effects and a canonical workspace-relative write scope in separate isolation. If any packet is invalid, launch none: starting the valid ones and fixing the rest later is a partial launch.
- Compare canonical scopes. Resolve symlinks, normalize paths and compare case-insensitively so an alias cannot hide a collision. A lexical check alone cannot prove symlink or runtime isolation.
- Delivery is not engagement. A delivered prompt or an acknowledgement proves transport only; reading it as a working worker is prompt-send optimism. Prove engagement from observable state: session output, tool activity, changed files.
- Capture before restart. Before a nudge, replacement or restart, capture the worker's observable state. A restart destroys the evidence of why it stalled, and rescue is usually cheaper than rerun. Silence or impatience alone does not justify a restart; any replacement stays within authority and remaining bounds.
- Dispatch once. Keep each packet's identity with its result. An executor error is a result, not a retry trigger; repair and follow-up are the caller's authority.
Roles
- Orchestrator: passes focused intent, scope and evidence references, names the integration/final-review owner, and reports runtime facts. Retrieve extra history only for a consequential uncertainty; a fresh context is not necessarily small. A new goal does not clear history or renew spent bounds.
- Implementer: may modify only its packet's declared subject.
- Validator: receives exact candidate content in a fresh, read-only context.
It may supply judgment to Validate; only Validate writes
verdict.v2. - Scribe: records runtime evidence without judging acceptance.
Reader and Writer are bounded cheap delegations, not roles with authority. A
Reader returns line-referenced bullets over files the caller never loads, in
slices of at most 350 lines. A Writer lands one patterned file from a spec plus
a required reference file and returns a receipt the caller never reads back.
Both are caller-selected per call and yield runtime facts only; a receipt is not
validation. For Codex, use the source-owned bulk-reader and code-writer
native roles; their model and sandbox are pinned in
agents/bulk-reader.toml and
agents/code-writer.toml.
Context-budget delegation covers
installation, native invocation, opt-in refusal hooks and the limits of role
instructions.
Show full SKILL.md (424 more words)Show less
Launch and observe
- Before starting a worker, require caller intent, role, workspace, authorized source/output scope and evidence destination. Record the dispatch association in the caller-owned native channel before execution can fail. A requested ID is not an observed ID; worker identity stays unknown until the runtime reports it.
- At startup, before substantive work, capture the observed runtime, session and context identity and return it through that channel. Report launch failures, recording gaps and unknowns; never fill them in. Session associations owns parent and resume links, multi-work spans and frozen source bounds.
- Keep concurrent writers disjoint and isolated. Runtime coordination is not a claim, lease, queue or completion state in AgentOps.
- Observe through native waits or status notifications; observation costs time and context. Unchanged state is no reason for another analysis, review or retrospective, while a known blocking failure deserves action even as other jobs run. Stop at terminal status or the end of the caller's window.
- For new authorized work after a worker completes, use the runtime's documented follow-up or resume operation that starts a turn. A message operation only queues text for a running worker; a queued repair request is not a resumed attempt.
- Record provider state, transcript references, artifacts and terminal status. Provider retries, reconnects, idle states and failures stay runtime facts, never Plan, Candidate or verdict state.
The batch contract's reference implementation, scripts/swarm/dispatch_once.py,
needs an AgentOps source checkout and is not bundled with installed skills;
installed use dispatches through the selected native runtime. It rejects a
nonempty write_scope.exclude because its proof cannot honor exclusions. Batch
mode selects no backlog work, creates no queue and integrates no changes.
Adapters and judgment
NTM, native processes, Agent Mail, Gas City and the one-shot headless runners (codex-exec, claude-exec, agy-native) are replaceable adapters. Use one only when the caller selected that execution shape; a single local agent pays no factory coordination cost.
For judgment, default to a fresh context in the author's model family. Cross-model Validate, mixed Council and dueling model perspectives are explicit caller selections. Model dispatch owns host authorization, isolation, finite input/output, timeout and cleanup for each leg; the working session is the controller, no factory is required, and Agent Mail is never the judgment path. Role requests declare authority, but only native runtime/OS filesystem and egress controls enforce it. Native judgment receipts define receipt references and the checks for caller-required model diversity; missing native identity never satisfies a leg. For exact native source spans, follow bounded raw source reads and its access and output limits.
Per-packet result
packet_id: the caller's packet id
executor: selected runtime; requested model; observed model if reported
observed_session: session/context id the runtime reported, else unknown
engagement: observable evidence the worker started, else unobserved
terminal_status: exit or terminal state | running | launch failed
result: candidate <ref> | evidence <ref> | error <verbatim>
gaps: recording failures and unknowns© boshu2, Apache-2.0. 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 8 other files (scripts, references) in skills/agent-native of boshu2/agentops.
- SKILL.md
- agents/bulk-reader.toml
- agents/code-writer.toml
- references/RAW_SOURCE_READS.md
- references/context-budget-delegation.md
- references/judgment-receipts.md
- references/model-dispatch.md
- references/session-associations.md
- scripts/fake_model_runner.py
Open the folder on GitHubat commit 3bdbfed
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in boshu2/agentops, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Agent Native 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Native this skillboshu2/agentops | 447 | 1 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
More from boshu2/agentops
All 31 skills in this repoCouncil
boshu2/agentops
Compare independent opinions from several models or contexts without inflating agreement.
Craft Goal
boshu2/agentops
Draft or lint a bounded long-running goal prompt with a finish line and hard limits.
Doc
boshu2/agentops
Write or update READMEs, docs, repo instructions and handoff notes, checked against source.
Idea Genie
boshu2/agentops
Brainstorm evidence-backed options for what to build, or stress-test an idea.
Implement
boshu2/agentops
Change or repair code, config or services without weakening tests; report what ran and what did not.
Memory
boshu2/agentops
Write, find or curate lessons and agent rules with stated evidence and limits.
Related
Categories
Questions about Agent Native
What does Agent Native do?
Dispatch independent tasks to parallel workers or subagents without write collisions. Agent Native is an agent skill from boshu2/agentops. Dispatch independent tasks to parallel workers or subagents without write collisions.
When should I use Agent Native?
Agent Native fits situations like: planning agents in parallel; check scopes before any launch.
How do I install Agent Native in Claude Code?
Run `npx skills add boshu2/agentops --skill agent-native -a claude-code`. Or copy the skill folder (skills/agent-native in boshu2/agentops) into .claude/skills/agent-native in your project. Claude Code loads it when a task matches its description.
How do I install Agent Native in Codex?
Run `npx skills add boshu2/agentops --skill agent-native -a codex`. Or copy the skill folder (skills/agent-native in boshu2/agentops) into .agents/skills/agent-native in your project. Codex loads it when a task matches its description.
Can I use Agent Native 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 boshu2/agentops --skill agent-native -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-native, .gemini/skills/agent-native, .github/skills/agent-native and .opencode/skills/agent-native in your project.
What does Agent Native need to run?
Going by SKILL.md and its folder, Agent Native needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Agent Native 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 Agent Native 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Agent Native use?
Agent Native is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Native use?
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.7k tokens, read only when the agent opens those files.
What are the alternatives to Agent Native?
Skills that share tags, products or a category with Agent Native: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Native?
boshu2 (a GitHub user) maintains it in boshu2/agentops, which has 447 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 7, 2026.
Source: boshu2/agentops on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.