Class-level Claude/Codex/delegate_task agent operations: background execution, stdin/print stalls, plugin IDs, worker patch loops, and fallback routing.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add vamseeachanta/workspace-hub --skill agent-cli-delegation-operations --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Agent Cli Delegation Operations?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vamseeachanta-agent-cli-delegation-operations-workspace-hub)More formats (shields.io, HTML) on the badges page.
---
name: agent-cli-delegation-operations
version: 1.0.0
category: autonomous-ai-agents
description: "Class-level Claude/Codex/delegate_task agent operations: background execution, stdin/print stalls, plugin IDs, worker patch loops, and fallback routing."
tags: [claude, codex, agents, delegation]
---
# Agent Cli Delegation Operations
## When to Use
Use when launching or supervising autonomous CLI agents, recovering stalled Claude/Codex runs, handling delegate_task limitations, routing failed Claude lanes to Codex, or maintaining plugin identity scope.
## Class-Level Workflow
1. Prefer explicit background process tracking and absolute logs over shell-disowned runs.
2. Close stdin for Codex modes that wait for EOF; salvage Claude print stalls by checking process state and logs.
- If a Codex background log contains only `Reading additional input from stdin...`, treat it as likely waiting for EOF or prompt delivery rather than useful progress. Re-check current `codex exec --help`, relaunch with a known-good stdin-close/input pattern, and verify output artifacts advance.
3. Poll by captured session IDs after launch; generic process lists can be empty even while known background sessions are still running. Treat `process list` as advisory, not authoritative, when session IDs are available.
4. For Gemini CLI lanes launched inside a repository, remember Gemini may auto-load `.gemini/agents/*.md`. Startup validation errors such as unsupported `permissionMode` keys can prevent useful work even while the wrapper remains alive; capture the error, run from a clean context or fix the agent definitions through a validated repo change.
5. Treat delegate_task lane limits as an orchestration constraint.
6. When a worker patches canonical skills, verify file paths and resulting content before reporting success.
7. Keep provider/agent fallback decisions evidence-based.
## Consolidated Session Learnings
The `references/` directory contains archived narrow skills absorbed during the 2026-04-29 umbrella consolidation pass. Use the subsections below as the class-level index, then open the named reference when a case-specific recipe is needed.
## Absorbed Narrow Skills (2026-04-29)
### `claude-delegated-issue-tree-expansion`
- Former skill demoted to `references/claude-delegated-issue-tree-expansion.md`.
- Preserved insight: Use Claude subagents for read-only gap analysis to expand an umbrella GitHub issue into a layered tree of focused child issues, then create the issues locally and update the issue map/docs.
### `claude-plugin-update-id-scope`
- Former skill demoted to `references/claude-plugin-update-id-scope.md`.
- Preserved insight: Fix Claude plugin update failures caused by using the short plugin name instead of the installed plugin id and wrong scope.
### `claude-print-stall-salvage`
- Former skill demoted to `references/claude-print-stall-salvage.md`.
- Preserved insight: Recover delegated Claude Code print-mode runs that stall silently or produce partial edits in large worktrees.
### `claude-worker-patch-loop`
- Former skill demoted to `references/claude-worker-patch-loop.md`.
- Preserved insight: Use Claude as a delegated worker to patch canonical skills or policy files directly, then verify and iterate from the main session.
### `codex-background-burn-orchestration`
- Former skill demoted to `references/codex-background-burn-orchestration.md`.
- Preserved insight: Run quota-aware Codex usage-burn waves as useful background issue-execution lanes, including Hermes stdin-close and sandbox recovery patterns.
### `codex-background-stdin-close`
- Former skill demoted to `references/codex-background-stdin-close.md`.
- Preserved insight: Launch Codex CLI background runs in Hermes when Codex hangs at `Reading additional input from stdin...`; use explicit process stdin close and isolated worktrees.
### `codex-skill-loader-broken-symlink-recovery`
- Former skill demoted to `references/codex-skill-loader-broken-symlink-recovery.md`.
- Preserved insight: Diagnose Codex startup failures in workspace-hub caused by a broken `.claude/skills/skills` symlink and recover without misattributing the failure to issue scope.
### `delegate-task-4-lane-workaround`
- Former skill demoted to `references/delegate-task-4-lane-workaround.md`.
- Preserved insight: Work around delegate_task batch concurrency cap when the user wants four parallel review lanes.
### `interactive-claude-to-file-based-fallback`
- Former skill demoted to `references/interactive-claude-to-file-based-fallback.md`.
- Preserved insight: Switch from tmux/interactive Claude Code to file-based claude -p execution when interactive runs fail with upstream errors or analysis-only stalls, then verify landing from git/GitHub state.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!