eobarretooo/clawlite/coding-agent
Claude Code and agent skill by eobarretooo/clawlite
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Orchestrate coding work with ClawLite sessions/subagents and patch tooling for multi-step implementation flows.
Install
npx vskill@latest install eobarretooo/clawlite/coding-agentSKILL.md
Coding Agent
Guide-only skill for delegating code tasks to spawned sessions/subagents and coordinating completion.
When to use
- Multi-file features, refactors, migrations, and bugfixes that benefit from isolated workers.
- Parallel tasks that need progress tracking and explicit integration.
- Issue-to-PR workflows where each unit should run in its own session.
Core tools
sessions_spawn: create focused workers with clear scope, timeout, and cleanup policy.subagents: run parallel autonomous tasks when decomposition is stable.session_status: monitor worker lifecycle, progress, and failure states.sessions_history: inspect outputs/artifacts before integrating.process: run build/test/git commands and poll long-running jobs.apply_patch: apply deterministic file edits for targeted changes.
Operating pattern
- Define scope, acceptance checks, and touched paths before spawning work.
- Spawn one worker per independent task with explicit constraints.
- Track status and collect outputs; rerun failed workers with narrowed prompts.
- Integrate patches incrementally, then run local validation commands.
- Prepare final summary with changed files, checks, and open risks.
Safety constraints
- Do not assume PTY or interactive terminal capabilities for skill execution.
- Prefer non-interactive commands and deterministic arguments.
- Require explicit user approval for destructive actions (
rm, hard reset, force push, mass delete, irreversible migrations). - Keep branch/repo hygiene: avoid unrelated edits, never discard user work, and report blocked operations clearly.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingclawlite/skills/coding-agent/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/eobarretooo/clawlite/coding-agent)