claude_code_agent
Wrapper agent for the external 'claude-code' tool.
Skill by dewitt
Chalk Labs
Need help deploying claude_code_agent?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dewitt-claude-code-agent
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/claude-code-agent
What's inside
- Skill name
claude_code_agent- Description
- Wrapper agent for the external 'claude-code' tool. Use this to delegate complex general-purpose coding spans, heavy refactoring, or broad codebase modifications to Claude Code.
- License
- Apache-2.0
- Instructions
- 22 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "claude_code_agent" does not match folder "claude-code"
Files (1)
- SKILL.md
SKILL.md (first lines)
You are the Claude Code wrapper agent. Your purpose is to delegate complex spans, heavy refactoring, or broad codebase modifications to the external `claude-code` tool. When the user requests a span that is best handled by `claude-code`, you must construct the appropriate command to execute it. You have access to the `bash_execute` tool to run commands. Usage: Use `bash_execute` to run `claude -p "<user request>" --dangerously-skip-permissions`. You MUST append `--dangerously-skip-permissions` to auto-approve file writes, otherwise you will hang the execution! **CRITICAL ERROR HANDLING:** If `bash_execute` returns an error indicating that the `claude` command is not found, authentication failed, or you lack budget/permissions, you MUST immediately stop trying to use it. Return a clear failure message to Swarm explicitly stating: "Claude Code CLI is unavailable or failed: [reason]. Do not route to me again for this span." Do not get stuck in a loop trying the same command. You MUST also invoke the `request_replan` tool to tell Swarm to re-route the task. Remember to clearly state that you are delegating the span to `claude-code` and report the outcome back to the user.
From dewitt/swarm, Apache-2.0.
More from dewitt/swarm
- 0.451score
sysadmin
dewitt
Specialized in diagnosing host operating systems, safely resolving missing dependencies, and installing required packages (via Homebrew, APT, npm, pip, go) so…
SkillDFreshness: D★ 4Claude Code +9 - 0.451score
lsp
dewitt
A powerful skill that gives the agent semantic understanding of a codebase via the Language Server Protocol (LSP), moving beyond text searches to true code…
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
skill-creator
dewitt
Specialized in autonomously researching and creating new dynamic skills for Swarm when a capability is missing.
SkillDFreshness: D★ 4Claude Code +9 - 0.447score
code_review
dewitt
Specialized agent for performing comprehensive codebase reviews, identifying architectural flaws, and enforcing idiomatic design.
SkillDFreshness: D★ 4Claude Code +9 - 0.447score
quality_review
dewitt
Specialized agent for evaluating Swarm trajectory efficiency, tool-use rigor, orchestration handoffs, and LLM-as-a-Judge grading rubrics.
SkillDFreshness: D★ 4Claude Code +9 - 0.446score
gemini_cli_agent
dewitt
Wrapper agent for the external 'gemini-cli' tool.
SkillDFreshness: D★ 4Claude Code +9 - 0.444score
codebase_investigator
dewitt
The specialized tool for codebase analysis, architectural mapping, and understanding system-wide dependencies.
SkillDFreshness: D★ 4Claude Code +9 - 0.443score
git_agent
dewitt
A fast and lightweight agent for handling Git operations like switching branches, checking status, committing, and managing source code chores.
SkillDFreshness: D★ 4Claude Code +9 - 0.443score
github_agent
dewitt
A specialized agent for interacting with GitHub using the GitHub CLI (gh), enabling fast management of pull requests, issues, and repository settings.
SkillDFreshness: D★ 4Claude Code +9 - 0.441score
codex_agent
dewitt
Wrapper agent for the external 'codex' CLI.
SkillDFreshness: D★ 4Claude Code +9 - 0.440score
input_agent
dewitt
Context guard and digression failsafe.
SkillDFreshness: D★ 4Claude Code +9 - 0.440score
gitops_agent
dewitt
Specialized in crafting CI/CD pipelines, writing GitHub Actions, and executing Git operations for deployment.
SkillDFreshness: D★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Mar 9, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/dewitt/swarm
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dewitt
- 0.451score
lsp
dewitt
A powerful skill that gives the agent semantic understanding of a codebase via the Language Server Protocol (LSP), moving beyond text searches to true code…
SkillDFreshness: D★ 4Claude Code +9 - 0.451score
sysadmin
dewitt
Specialized in diagnosing host operating systems, safely resolving missing dependencies, and installing required packages (via Homebrew, APT, npm, pip, go) so…
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
skill-creator
dewitt
Specialized in autonomously researching and creating new dynamic skills for Swarm when a capability is missing.
SkillDFreshness: D★ 4Claude Code +9 - 0.447score
quality_review
dewitt
Specialized agent for evaluating Swarm trajectory efficiency, tool-use rigor, orchestration handoffs, and LLM-as-a-Judge grading rubrics.
SkillDFreshness: D★ 4Claude Code +9 - 0.447score
code_review
dewitt
Specialized agent for performing comprehensive codebase reviews, identifying architectural flaws, and enforcing idiomatic design.
SkillDFreshness: D★ 4Claude Code +9 - 0.446score
gemini_cli_agent
dewitt
Wrapper agent for the external 'gemini-cli' tool.
SkillDFreshness: D★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get claude_code_agent running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
claude_code_agent skill. Agent Mart. https://agentmart.dev/skills/dewitt-claude-code-agent (last updated 2026-10-24)