ramblurr/coding-agents
prompts/skills/coding-agents/SKILL.md
Spawn and control external coding agents (Claude Code, Codex, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running multiple agents in parallel on separate issues, (4) spawning an agent in an isolated environment or worktree, (5) user mentions "codex", "pi agent", or running "another claude".
tools
Updated May 21, 2026
$ install --global
skillsauthnpx skillsauth add ramblurr/nix-devenv coding-agentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 21, 2026, 5:43 AM139.2s5 files scanned
SKILL.md
- name:
- coding-agents
- description:
- Spawn and control external coding agents (Claude Code, Codex, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running multiple agents in parallel on separate issues, (4) spawning an agent in an isolated environment or worktree, (5) user mentions "codex", "pi agent", or running "another claude".
Coding Agents
Orchestrate external coding agents programmatically. Use this when you want to delegate tasks to other AI coding tools.
Always prefer to use Pi as a subagent along with Skill(pi-link-coordination) and Skill(tmux), unless told otherwise.
Prefer interactive mode
Interactive sessions via tmux should be the default for most tasks. Background mode is only appropriate for the simplest tasks that require very few commands or edits (e.g., "count the files in src/", "what version of node is this project using?").
Why interactive is better:
- You can observe progress and catch issues early
- You can respond if the agent asks clarifying questions
- You can interrupt if the agent goes off track
- Agents often need multiple turns to complete real work
- Debugging is much easier when you can see what happened
Use background mode only when:
- The task is trivial (one or two simple commands)
- You are confident the agent will complete without interaction
- You are running many parallel tasks and cannot watch them all
Interactive mode requires the tmux Skill
For interactive sessions, you MUST use the tmux Skill. The tmux Skill contains:
- "Orchestrating Claude Code sub-agents" recipe - the primary pattern for this use case
- Socket conventions and session management
- Sending input, monitoring output, cleanup
Read and follow the tmux Skill for all interactive agent orchestration.
For parallel work on multiple issues, use the git worktrees Skill to create isolated branches.
Available agents
Read the relevant reference file for the agent you need right now:
- references/claude-code.md - Anthropic's Claude Code CLI
- references/codex.md - OpenAI's Codex CLI
- references/pi.md - Pi, Lightweight multi-provider agent
Each reference includes: invocation, key flags, and completion detection.
Rules
- Respect tool choice - if user asks for Codex, use Codex. Do not offer to do the task yourself.
- Be patient - do not kill sessions because they seem slow. Agents take time.
- Monitor without interfering - check progress but let the agent work.
- Use appropriate flags - permission-bypassing flags for unattended/background work only.
- Isolate work - use worktrees or temp directories to avoid conflicts with your current work.
- Clean up - kill sessions and remove worktrees when done, unless the user asked you not to.
Related Skills
ramblurr/nixbot
tools
VerifiedTrustedCommunity
Use when working with Nixbot CI, forge commit statuses, Nix flake checks, nixbot.toml, Nixbot effects, or nixbot-cli - explains how Nixbot runs flake CI and how to inspect builds and logs.
SKILL.mdUpdated Jun 12, 2026
ramblurr/operational-change-protocol
testing
VerifiedTrustedCommunity
Use this OCP when executing or preparing to execute commands that change a live or important system, service reloads/restarts, package changes, deployments, migrations, firewall/network/access changes, credential rotation, NixOS switch/test/boot/deploy, or incident mitigation. It guides safe operations with a persisted ledger for scope, preflight, baseline, rollback, validation, and evidence.
SKILL.mdUpdated Jun 4, 2026
ramblurr/write-a-skill
development
VerifiedTrustedCommunity
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
SKILL.mdUpdated May 21, 2026
ramblurr/prompts-documents
documentation
VerifiedTrustedCommunity
Naming conventions for workflow documents in prompts/. Use when creating plans, PRDs, research reports, idea capture or other workflow documents. Triggers on (1) creating new planning documents, (2) naming PRDs or research reports, (3) questions about document organization in prompts/.
SKILL.mdUpdated May 21, 2026