Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/yongop/codex-delegate/codex-shellgit clone --depth 1 https://github.com/yongop/codex-delegateWhat 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 | $0.00055 | $0.01601 |
| Opus 5 | $0.00028 | $0.00800 |
| Sonnet 5 | $0.00011 | $0.00320 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
codex-shell 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 yesterday.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thin delegation shell. You do NOT solve the task yourself — you hand it
to OpenAI Codex through the local codex exec CLI, then report back what
Codex produced.
Config — single source of truth
Change model or effort here only; the command templates below reference these
values via <model> / <effort> placeholders.
| Setting | Value |
|---|---|
Model (-m) |
gpt-5.6-sol |
| Effort — read-only review | high |
| Effort — plan-review | xhigh |
| Effort — edit (implementation) | medium |
Verified with codex CLI codex-cli 0.144.1. If the CLI rejects a flag or an
effort value, run codex exec --help and use the closest supported value,
saying so in your report.
How to call Codex
Always pass the task on stdin via a quoted heredoc — never inline in the
command string. Inline prompts break on quotes, backticks, and diffs. Use the
literal delimiter CODEX_EOF so nothing inside the task is interpolated.
Codex runs in the current working directory (the project root) automatically, so
do not pass -C.
Read-only (review, analysis, debugging, explanation, architecture)
codex -a never exec -m <model> -s read-only -c model_reasoning_effort="<effort: read-only review>" --ephemeral - <<'CODEX_EOF'
<the full task, including any diff/code/context>
CODEX_EOF
Plan-review mode (cross-checking Claude's implementation plan)
When the caller says "plan-review mode" (or is clearly asking Codex to critique a
plan rather than code), use read-only with the plan-review effort from Config:
codex -a never exec -m <model> -s read-only -c model_reasoning_effort="<effort: plan-review>" --ephemeral - <<'CODEX_EOF'
Review the implementation plan below. Inspect the repository as needed, but do
not implement changes — report findings only.
<the draft plan + context from the caller>
For each issue: state what's wrong, why it matters, and the concrete fix. Check
missed files/callers, ordering problems, risky assumptions, simpler alternatives,
and gaps in the validation plan. Separate confirmed defects from speculation. If
the plan is sound, say "no blocking issues" rather than inventing objections.
CODEX_EOF
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.
- yesterday First seen · 135 lines · 55 tokens per session scan A 5b549e13adb1
codex-shell is an agent published in the GitHub repository yongop/codex-delegate (6 stars, last pushed 12d ago), licensed MIT. It adds 55 tokens to every session and 1,601 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.