Borrowing it
Nothing to install: this file belongs to changoo89/claude-pilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/changoo89/claude-pilot/main/.claude/skills/gpt-delegation/SKILL.mdgit clone --depth 1 https://github.com/changoo89/claude-pilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/changoo89/claude-pilot/gpt-delegation)<a href="https://agentmods.dev/skills/changoo89/claude-pilot/gpt-delegation"><img src="https://agentmods.dev/badge/skills/changoo89/claude-pilot/gpt-delegation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/changoo89/claude-pilot/gpt-delegation"><img src="https://agentmods.dev/badge/skills/changoo89/claude-pilot/gpt-delegation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.01621 |
| Opus 5 | $0.00015 | $0.00811 |
| Sonnet 5 | $0.00006 | $0.00324 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
gpt-delegation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: GPT Delegation
Purpose: Intelligent Codex/GPT consultation for complex problems, escalation when stuck
Quick Start
When to Use
- After 2+ failed attempts on same issue
- Architecture decisions needed
- Security concerns
- Ambiguous requirements
- Plan review for large plans (5+ SCs)
- Proactive consultation: Before asking user when confidence < 0.5 (see rubric below)
Quick Reference
# Graceful fallback + delegation (see CRITICAL WARNING below for valid parameters)
if ! command -v codex &> /dev/null; then
echo "Warning: Codex CLI not installed - falling back to Claude-only analysis"
return 0
fi
codex exec -m gpt-5.2 -s workspace-write -c reasoning_effort=medium --json "TASK: [goal]
EXPECTED: [outcome], CONTEXT: [attempts, errors, iteration], MUST: Analyze failures, fresh approach, report files"
Core Concepts
Graceful Fallback (CRITICAL)
MANDATORY: All GPT delegation points MUST include graceful fallback.
if ! command -v codex &> /dev/null; then
echo "Warning: Codex CLI not installed - falling back to Claude-only analysis"
return 0 # NOT an error, continue with Claude
fi
Key Points:
- Graceful fallback is NOT an error
- Log warning message
- Return success (exit 0) to allow continuation
- Continue with Claude agents
CRITICAL WARNING: Codex CLI Parameters (READ CAREFULLY)
MANDATORY: Use EXACT values below - NO variations allowed
Valid -s modes: read-only | workspace-write | danger-full-access
FORBIDDEN: workspace-read, read-write, write (Claude often creates invalid combinations)
Valid -c value: reasoning_effort=medium ONLY (NOT high/low)
Required: -m gpt-5.2 --json "PROMPT"
Delegation Triggers
| Trigger | Expert | Mode | When to Delegate |
|---|---|---|---|
| 2+ failed attempts | Architect | workspace-write | Progressive escalation |
| Stuck on task | Architect | workspace-write | Fresh perspective |
| Architecture decision | Architect | read-only | Design guidance |
| Security concern | Security Analyst | read-only | Vulnerability assessment |
| Ambiguous plan | Scope Analyst | read-only | Requirements clarification |
| Large plan (5+ SCs) | Plan Reviewer | read-only | Plan validation |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 181 lines · 29 tokens per session scan A 99d72ede71cd
gpt-delegation is a skill published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 1,621 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.
finance
Financial analysis expertise for financial modeling (DCF, LBO, M&A), valuation, financial statement analysis, capital allocation, treasury management, and corporate finance decisions. Use when building financial models, analyzing statements, or making investment decisions.