Kimi Code Delegation
CherryHQ/cherry-studio
Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.
Draft a new Claude Code subagent at .claude/agents/<name.md, using the official subagents format.
Install Ad Subagent
$ npx skills add CorridorTech/PoseCap --skill ad-subagent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CorridorTech/PoseCap ad-subagent --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/CorridorTech/PoseCap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ad-subagent .claude/skills/ad-subagent && 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 "ad-subagent" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-subagent into .claude/skills/ad-subagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-subagent", 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/CorridorTech/PoseCap/tree/main/.claude/skills/ad-subagentType 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 CorridorTech/PoseCap --skill ad-subagent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CorridorTech/PoseCap ad-subagent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/ad-subagent .agents/skills/ad-subagent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ad-subagent" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-subagent into .agents/skills/ad-subagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-subagent", 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 CorridorTech/PoseCap --skill ad-subagent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CorridorTech/PoseCap ad-subagent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/ad-subagent .cursor/skills/ad-subagent && 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 "ad-subagent" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-subagent into .cursor/skills/ad-subagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-subagent", 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/CorridorTech/PoseCap.git --path .claude/skills/ad-subagent--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 CorridorTech/PoseCap --skill ad-subagent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CorridorTech/PoseCap ad-subagent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/ad-subagent .gemini/skills/ad-subagent && 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 "ad-subagent" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-subagent into .gemini/skills/ad-subagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-subagent", 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 CorridorTech/PoseCap ad-subagentInstalls 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 CorridorTech/PoseCap --skill ad-subagent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/ad-subagent .github/skills/ad-subagent && 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 "ad-subagent" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-subagent into .github/skills/ad-subagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-subagent", 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 CorridorTech/PoseCap --skill ad-subagent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CorridorTech/PoseCap ad-subagent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/ad-subagent .opencode/skills/ad-subagent && 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 "ad-subagent" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-subagent into .opencode/skills/ad-subagent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-subagent", 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
ad-subagent- GitHub stars
- 224
- Token cost
- ~1.3k tokens
- SKILL.md length
- 586 words
- Files
- 1
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Draft a new Claude Code subagent at .claude/agents/<name.md, using the official subagents format.
- Works in 5 steps: Confirm target → Pick a pattern (or build custom) → Interview to fill → …
- The user wants to create
- SKILL.md covers Step 1 — Confirm target, Step 2 — Pick a pattern (or…, Step 3 — Interview to fill and Step 4 — Write the file, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Ad Subagent is an agent skill from CorridorTech/PoseCap. Draft a new Claude Code subagent at .claude/agents/<name.md, using the official subagents format. Use when the user wants to create, write, draft, or scaffold a custom Claude Code subagent for delegated work (fresh-context reviewer, codebase researcher, docs researcher, test designer, bug reproducer, bounded implementation worker). Asks one question per missing field; never invents roles or tool sets.
Its SKILL.md is about 1.3k 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 Agent Workflows, covering Subagents. It works with Bash. The licence is Apache-2.0.
When your agent uses it
- The user wants to create
- Scaffold a custom Claude Code subagent for delegated work (fresh-context reviewer
- Codebase researcher
- Docs researcher
Example prompts
- “/ad-subagent”
Requirements
- Pre-approved tools (allowed-tools): Read, Write, Glob, Bash
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 626701b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteGlobBash
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
Links to these hosts (documentation or services it may open):
code.claude.com
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
Ad Subagent loads about 1.3k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 586 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Write, Glob, Bash
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 CorridorTech/PoseCap at commit 626701b, republished under its Apache-2.0 licence (© CorridorTech). 586 words, ~1,279 tokens.
Download SKILL.mdSave it as
.claude/skills/ad-subagent/SKILL.md (or your agent's skills folder).- name
- ad-subagent
- description
- Draft a new Claude Code subagent at .claude/agents/<name>.md, using the official subagents format. Use when the user wants to create, write, draft, or scaffold a custom Claude Code subagent for delegated work (fresh-context reviewer, codebase researcher, docs researcher, test designer, bug reproducer, bounded implementation worker). Asks one question per missing field; never invents roles or tool sets.
- allowed-tools
- Read, Write, Glob, Bash
- summary
- Draft a host-specific custom subagent for bounded delegated work — Claude Code `.claude/agents/<name>.md`, Codex `.codex/agents/<name>.toml`.
/ad-subagent
Drafts .claude/agents/<name>.md (project) or ~/.claude/agents/<name>.md (personal). Spec: code.claude.com/docs/en/sub-agents.
The body becomes the subagent's role prompt. A named subagent starts with fresh conversation context and its own tools/model settings; do not rely on parent-session memory. Restate task-specific constraints and cite any project files it must follow.
Step 1 — Confirm target
Ask the user:
- Name — kebab-case, lowercase. Becomes the file name and the routing handle (
subagent_type: '<name>'). - Personal or project —
~/.claude/agents/<name>.md(personal) vs.claude/agents/<name>.md(project, committed). Default: project.
Step 2 — Pick a pattern (or build custom)
Common pre-baked shapes (from prompts/subagent.md):
| Pattern | Tools | Model | Notes |
|---|---|---|---|
| Fresh-context reviewer | Read, Glob, Grep, Bash | sonnet | Matches WORKFLOW §10. No write tools. |
| Codebase researcher | use built-in Explore | inherit | Don't build custom unless you need different tools. |
| Diff-only auditor | Read, Bash | sonnet | Pair with permissionMode: dontAsk for read-only runs. |
| Docs researcher | Read, WebFetch or docs MCP | inherit | Confirms versioned APIs; returns citations only. |
| Test designer | Read, Glob, Grep | inherit | Proposes public-interface tests from spec/task; no production edits. |
| Bug reproducer | Read, Bash, Write | inherit | Builds the smallest failing loop, then stops before broad fixes. |
| Bounded worker | scoped write tools | inherit | Owns a disjoint file/module set; returns changed paths + verification. |
Built-in subagents (Explore, Plan, general-purpose) cover most cases. Build custom only when you need a specific role, scoped tools, persistent memory, or a different model.
Delegation-fit gate: build a custom subagent only when the role repeats, the work is self-contained, the output can be summarized or bounded to a disjoint patch, or the role needs tool/model/sandbox restrictions. Keep frequent back-and-forth, tightly coupled implementation, and the immediate blocking step in the main conversation.
Step 3 — Interview to fill
Ask one question per missing field, in this order:
- Role — one sentence: "You are a
<role>that<does X>when<triggered by Y>." - Description — the routing signal. Specific, includes the task framings the parent agent would recognize. Claude reads this to decide whether to delegate.
- Tools — comma-separated list. Limit deliberately. A reviewer with
Writeaccess stops being a reviewer. Omit to inherit all parent tools. - Model —
sonnet | opus | haiku | inherit. Default:inherit. - Output contract — what the subagent returns to the caller. Be explicit about format.
- Stop criterion — when the subagent should stop and return control.
Do not invent values. When the user does not know something, ask. Do not invent frontmatter fields not in the spec.
Show full SKILL.md (201 more words)Show less
Step 4 — Write the file
Path: .claude/agents/<name>.md (project, committed) or ~/.claude/agents/<name>.md (personal). Frontmatter uses the Claude Code subagents shape (see code.claude.com/docs/en/sub-agents) — declare only the fields the subagent actually uses.
Body = the role prompt. Every line costs tokens on every subagent turn. Be terse. State role, scope, output format, stop criterion, and what NOT to do. Restate task-specific constraints and point to project files for load-bearing conventions.
Edits to subagent files on disk require a session restart to take effect; agents created via Claude Code's /agents UI take effect immediately.
Step 5 — Stop after writing
Do not dispatch to the new subagent, do not test it. The user will exercise it themselves.
Output contract
A single new file at .claude/agents/<name>.md (or ~/.claude/agents/<name>.md). Frontmatter declares only the fields actually used. Body is the system prompt: terse, imperative, with explicit stop criterion. No external file dependencies the user did not ask for.
Next
- Test the new subagent by exercising the workflow it serves — invoke via the
Tasktool withsubagent_type: '<name>'. - Document the subagent in
AGENTS.md(or the project's operational guide) if it is project-wide rather than personal. - If the subagent ships alongside a skill (manifest-listed), update the skill's
manifest.jsonto declare the file.
© CorridorTech, 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
Just SKILL.md in .claude/skills/ad-subagent of CorridorTech/PoseCap.
Open the folder on GitHubat commit 626701b
Compare with similar skills
Ad Subagent 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 |
|---|---|---|---|---|---|---|
| Ad Subagent this skillCorridorTech/PoseCap | 224 | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | |
| Kimi Code DelegationCherryHQ/cherry-studio | 52k | 1 repos | ~504 | Automated safety check: Pass | AGPL-3.0 | |
| Teamethanhq/cc-fleet | 215 | 1 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 | |
| Subagentethanhq/cc-fleet | 215 | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | |
| Agent Factoryalirezarezvani/claude-code-skill-factory | 880 | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Workflowethanhq/cc-fleet | 215 | — | ~5.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Team
ethanhq/cc-fleet
Spawn long-lived provider LLM teammates in tmux panes that you message via the native agent-team tools — multi-turn, collaborative, watchable.
Subagent
ethanhq/cc-fleet
Run a one-shot or flat parallel batch of provider LLM subagents (headless cc-fleet subagent) that return a result.
Agent Factory
alirezarezvani/claude-code-skill-factory
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
Workflow
ethanhq/cc-fleet
Orchestrate a MULTI-PHASE, dependent, or resumable run over many provider subagents from a JS script, off the main context (cc-fleet workflow).
- Official
Subagent Orchestration
PostHog/code
How and when to delegate work to subagents via the subagent tool (Explore, Plan, General).
More from CorridorTech/PoseCap
All 15 skills in this repoAd Adr
CorridorTech/PoseCap
Draft a new ADR (Architecture Decision Record) at doc/adr/NNNN-<short-title.md, using Michael Nygard's Context/Decision/Consequences/Alternatives pattern.
Ad Architecture
CorridorTech/PoseCap
Generate ARCHITECTURE.md at the repo root by scanning the code first, pre-filling layers/patterns/observability/deployment from observed signals, then asking only the genuine gaps.
Ad Archive
CorridorTech/PoseCap
Hard-delete completed plan files (tasks Status:done, specs Status:shipped, PRDs Status:superseded, ADRs Status:superseded or deprecated) via git rm, leaving git history as the only ledger.
Ad Drift
CorridorTech/PoseCap
Read-only drift audit — compare AGENTS.md, ARCHITECTURE.md, ADR statuses, feature specs in doc/specs/, and documentation discipline against what the code actually does.
Ad Hooks
CorridorTech/PoseCap
Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).
Ad Next
CorridorTech/PoseCap
Survey the project's state across the six-layer artifact stack and recommend prioritized next actions, modeled on flutter doctor.
Related
Works with
Categories
Questions about Ad Subagent
What does Ad Subagent do?
Draft a new Claude Code subagent at .claude/agents/<name.md, using the official subagents format. Ad Subagent is an agent skill from CorridorTech/PoseCap.md, using the official subagents format.
When should I use Ad Subagent?
Ad Subagent fits situations like: the user wants to create; scaffold a custom Claude Code subagent for delegated work (fresh-context reviewer; codebase researcher; docs researcher.
How do I install Ad Subagent in Claude Code?
Run `npx skills add CorridorTech/PoseCap --skill ad-subagent -a claude-code`. Or copy the skill folder (.claude/skills/ad-subagent in CorridorTech/PoseCap) into .claude/skills/ad-subagent in your project. Claude Code loads it when a task matches its description.
How do I install Ad Subagent in Codex?
Run `npx skills add CorridorTech/PoseCap --skill ad-subagent -a codex`. Or copy the skill folder (.claude/skills/ad-subagent in CorridorTech/PoseCap) into .agents/skills/ad-subagent in your project. Codex loads it when a task matches its description.
Can I use Ad Subagent 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 CorridorTech/PoseCap --skill ad-subagent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ad-subagent, .gemini/skills/ad-subagent, .github/skills/ad-subagent and .opencode/skills/ad-subagent in your project.
What does Ad Subagent need to run?
SKILL.md names no scripts, command-line tools or credentials: Ad Subagent is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Glob, Bash.
Does Ad Subagent access the network?
SKILL.md names 1 domain. As links in the text: code.claude.com. This is read from the text; nothing was executed.
Is Ad Subagent safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Ad Subagent use?
Ad Subagent 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 Ad Subagent use?
About 1.3k tokens (SKILL.md is roughly 5.1k 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 Ad Subagent?
Skills that share tags, products or a category with Ad Subagent: Kimi Code Delegation (CherryHQ/cherry-studio, 52k stars), Team (ethanhq/cc-fleet, 215 stars), Subagent (ethanhq/cc-fleet, 215 stars) and Agent Factory (alirezarezvani/claude-code-skill-factory, 880 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ad Subagent?
CorridorTech (a GitHub organization) maintains it in CorridorTech/PoseCap, which has 224 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.
Source: CorridorTech/PoseCap on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.