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 commands/backspacevenkat/polydev-claude-code-plugin/helpgit clone --depth 1 https://github.com/backspacevenkat/polydev-claude-code-pluginWhat 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 | $0.00011 | $0.00528 |
| Opus 5 | $0.00005 | $0.00264 |
| Sonnet 5 | $0.00002 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
help 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.
What it actually says
/polydev-help - Polydev Setup and Usage Guide
Display help information about Polydev multi-model AI consultation.
Response Template
When the user runs /polydev-help, respond with:
Polydev - Multi-Model AI Consultation
Query 4 AI models simultaneously. Get unstuck faster with diverse perspectives from GPT-5, Gemini, Grok, and GLM.
Quick Start
# 1. Login (opens browser, auto-configures token)
/polydev-login
# 2. Use it
/polydev How should I structure my React state?
Available Commands
| Command | Description |
|---|---|
/polydev [question] |
Get multi-model AI perspectives on any problem |
/polydev-login |
Authenticate via browser (recommended) |
/polydev-auth |
Check authentication status and credits |
/perspectives |
Alias for /polydev |
/polydev-help |
Show this help message |
Usage Examples
When debugging:
/polydev I'm getting a TypeError in my React component when mapping over an array
When choosing technologies:
/polydev Should I use Redis or PostgreSQL for session storage?
When reviewing code:
/polydev Review this authentication flow for security issues
How It Works
- You describe your problem or question
- Polydev queries 4 AI models in parallel:
- GLM-4.7 (Zhipu AI)
- Gemini 3 Flash (Google)
- Grok 4.1 Fast (xAI)
- GPT-5 Mini (OpenAI)
- You get synthesized insights showing:
- Where models agree (high confidence)
- Where models differ (needs consideration)
- Actionable recommendations
Pricing
| Tier | Credits | Cost |
|---|---|---|
| Free | 500/month | $0 (no card required) |
| Premium | 10,000/month | $10/month |
1 credit = 1 request (queries all 4 models)
Support
- Dashboard: polydev.ai/dashboard
- Docs: polydev.ai/docs
- Email: [email protected]
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 · 85 lines · 11 tokens per session scan A 074a259a0f03
help is a command published in the GitHub repository backspacevenkat/polydev-claude-code-plugin (0 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 528 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.