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.
git clone --depth 1 https://github.com/backspacevenkat/polydev-claude-code-pluginWrote 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/commands/backspacevenkat/polydev-claude-code-plugin/login)<a href="https://agentmods.dev/commands/backspacevenkat/polydev-claude-code-plugin/login"><img src="https://agentmods.dev/badge/commands/backspacevenkat/polydev-claude-code-plugin/login/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/commands/backspacevenkat/polydev-claude-code-plugin/login"><img src="https://agentmods.dev/badge/commands/backspacevenkat/polydev-claude-code-plugin/login.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 | $0.00007 | $0.01000 |
| Opus 5.5 | $0.00003 | $0.00400 |
| Sonnet 5.5 | $0.00001 | $0.00200 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
login scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "https://www.polydev.ai/api/auth/cli-session/${SESSION_ID}" \ How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polydev-login - Browser Authentication
Login to Polydev directly from your IDE or sandboxed environment.
Instructions
When the user runs /polydev-login:
Step 1: Check if MCP tools are available
Look for tools starting with mcp__plugin_polydev_mcp__ in your available tools list.
Step 2a: If MCP tools ARE available
Call the login tool:
mcp__plugin_polydev_mcp__login({ open_browser: true })
If browser login fails or the environment is sandboxed, the user can pass their token directly:
mcp__plugin_polydev_mcp__login({ user_token: "pd_user_token_here" })
Get the token from https://polydev.ai/dashboard
Step 2b: If MCP tools are NOT available (Cowork / sandboxed environments)
Use this bash-based login flow instead:
# Generate a unique session ID
SESSION_ID=$(openssl rand -hex 32)
# Create the login session on the server
curl -s -X POST "https://www.polydev.ai/api/auth/cli-session/${SESSION_ID}" \
-H "Content-Type: application/json"
# Generate the auth URL
echo ""
echo "========================================="
echo " Open this URL in your browser to login:"
echo "========================================="
echo ""
echo "https://polydev.ai/auth?session_id=${SESSION_ID}&redirect=ide-plugin&auto=true"
echo ""
echo "Waiting for authentication..."
Show the auth URL to the user and ask them to open it in their browser.
Then poll for the token:
# Poll every 3 seconds for up to 5 minutes
for i in $(seq 1 100); do
RESULT=$(curl -s "https://www.polydev.ai/api/auth/cli-session/${SESSION_ID}")
STATUS=$(echo "$RESULT" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('status',''))" 2>/dev/null)
if [ "$STATUS" = "completed" ]; then
TOKEN=$(echo "$RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))" 2>/dev/null)
if [ -n "$TOKEN" ]; then
# Save token to config files
mkdir -p ~/.config/polydev
echo "POLYDEV_USER_TOKEN=${TOKEN}" > ~/.polydev.env
# Add to shell config if not already present
if ! grep -q "POLYDEV_USER_TOKEN" ~/.zshrc 2>/dev/null && ! grep -q "POLYDEV_USER_TOKEN" ~/.bashrc 2>/dev/null; then
SHELL_RC="$HOME/.bashrc"
[ -f "$HOME/.zshrc" ] && SHELL_RC="$HOME/.zshrc"
echo "" >> "$SHELL_RC"
echo "# Polydev AI token" >> "$SHELL_RC"
echo "export POLYDEV_USER_TOKEN=\"${TOKEN}\"" >> "$SHELL_RC"
fi
echo ""
echo "Login successful! Token saved."
echo "Please restart your IDE for the token to take effect."
break
fi
fi
if [ "$STATUS" = "expired" ] || [ "$STATUS" = "not_found" ]; then
echo "Session expired or not found. Please try again."
break
fi
sleep 3
done
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.
- 2mo ago First seen · 122 lines · 7 tokens per session scan A 95a6acad8f93
login is a command published in the GitHub repository backspacevenkat/polydev-claude-code-plugin (1 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 1,000 once invoked, about $0.0000 per session on Opus 5.5. 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.
login compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| loginbackspacevenkat/polydev-claude-code-plugin | Command | 1 | today | MIT | A | 7 | Claude Code |
| auto-browsemarcusquinn/aidevops | Command | 439 | today | MIT | A | 18 | Claude Code |
| webapp-testinghamr0/agentic-toolkit | Command | 23 | 6d ago | Apache-2.0 | A | 35 | Claude Code |
| verify-prdesplega-ai/qa-use | Command | 29 | 1mo ago | MIT | A | 0 | Claude Code |
| gh-issue-use-cypressskyfox675/agents-skills | Command | 11 | today | MIT | A | 49 | Claude Code |
| readinesscygaco/master-console | Command | 111 | 17d ago | AGPL-3.0 | A | 51 | Claude Code |
| can-i-useivklgn/ai-kit | Command | 12 | 1mo ago | MIT | A | 13 | Claude Code |