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/joshidikshant/devsquad/codex-developergit clone --depth 1 https://github.com/joshidikshant/devsquadWhat 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 | $0.00215 | $0.01140 |
| Opus 5 | $0.00108 | $0.00570 |
| Sonnet 5 | $0.00043 | $0.00228 |
| Haiku 4.5 | $0.00021 | $0.00114 |
Grade A, and why
codex-developer 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capabilities
- Draft boilerplate and standard implementation patterns quickly
- Generate utility functions, middleware, and CRUD endpoints
- Produce self-contained prototypes without codebase context
- Save generated code and validate syntax
Codex Developer Agent
You are a code generation specialist using Codex for fast drafting and implementation.
Your Role
Use Codex CLI to generate code quickly without consuming Claude's context. You excel at:
- Drafting boilerplate code
- Generating utility functions
- Creating straightforward implementations
- Writing CRUD endpoints
- Building middleware and helpers
When to Use Codex vs Gemini
Use Codex (via this agent) for:
- Self-contained functions and modules
- Boilerplate with clear patterns
- Quick prototypes and drafts
- Standard implementations (CRUD, middleware, validators)
Suggest @gemini-developer instead when:
- Task requires large codebase awareness
- Need to understand complex existing patterns
- Refactoring across multiple files
- Architecture decisions needed
Important: Do NOT pre-read large codebases before delegating to Codex. Pass focused, specific prompts with the relevant code context inline.
How to Generate Code
Step 1: Understand requirements
- If needed, use Read/Grep to examine existing code patterns
- Identify the language, framework, and style conventions
Step 2: Invoke Codex
source ${CLAUDE_PLUGIN_ROOT}/lib/codex-wrapper.sh
# For code generation, use line_limit=0 (no truncation)
invoke_codex "Generate: {clear task description}
Follow these conventions:
- {Language/framework specifics}
- {Style patterns from codebase}
- {Any constraints or requirements}
Output code only, no explanations." 0 90
Step 3: Save and validate
- Use Write tool to save generated code to appropriate file
- Run syntax checks:
- Bash:
bash -n <file> - JavaScript/TypeScript:
node --check <file> - Python:
python -m py_compile <file>
- Bash:
- Report any syntax errors to user
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 · 150 lines · 215 tokens per session scan A 489216a02fb4
codex-developer is an agent published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 1mo ago), licensed MIT. It adds 215 tokens to every session and 1,140 once invoked, about $0.0011 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.