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/askgit 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 | $0.00009 | $0.00841 |
| Opus 5 | $0.00005 | $0.00420 |
| Sonnet 5 | $0.00002 | $0.00168 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
ask scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use curl to call the Polydev API directly: How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polydev-ask [question] - Get Multi-Model AI Perspectives
Query multiple AI models (GPT-5, Gemini, Grok, GLM) simultaneously to get diverse perspectives on any coding problem.
Instructions
When the user runs /polydev-ask [question], do the following:
-
Extract the question: Parse the argument after
/polydev-askas the question. If no question is provided, look at the recent conversation context. -
Enhance the question: Add relevant context from:
- Current file being worked on
- Recent errors or debugging attempts
- Project structure if relevant
-
Check if MCP tools are available by looking for
mcp__plugin_polydev_mcp__get_perspectivesin your tools.
If MCP tools ARE available:
Call the perspectives tool:
mcp__plugin_polydev_mcp__get_perspectives({
prompt: "The enhanced question with full context"
})
If MCP tools are NOT available (Cowork / sandboxed environments):
Use curl to call the Polydev API directly:
# Load token if not in env
[ -z "$POLYDEV_USER_TOKEN" ] && [ -f "$HOME/.polydev.env" ] && source "$HOME/.polydev.env"
if [ -z "$POLYDEV_USER_TOKEN" ]; then
echo "Not authenticated. Run /polydev:login first."
exit 1
fi
curl -s -X POST "https://www.polydev.ai/api/mcp" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $POLYDEV_USER_TOKEN" \
-H "User-Agent: polydev-mcp/1.9.0" \
-d '{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "get_perspectives",
"arguments": {
"prompt": "YOUR ENHANCED QUESTION HERE"
}
},
"id": "1"
}'
- Synthesize the response:
- Highlight areas of consensus (high confidence)
- Note where models differ (needs consideration)
- Provide actionable recommendations
Example Usage
User: /polydev-ask How should I structure my React state management?
Claude calls (if MCP tools available):
mcp__plugin_polydev_mcp__get_perspectives({
prompt: "How should I structure state management in a React application? I'm building a dashboard with real-time updates, user preferences, and form state."
})
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 · 105 lines · 9 tokens per session scan A 97e07c703209
ask is a command published in the GitHub repository backspacevenkat/polydev-claude-code-plugin (0 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 841 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.