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/intellegix/intellegix-code-agent-toolkit/labs-perplexitygit clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkitWhat 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 | $0.00000 | $0.01868 |
| Opus 5 | $0.00000 | $0.00934 |
| Sonnet 5 | $0.00000 | $0.00374 |
| Haiku 4.5 | $0.00000 | $0.00187 |
Grade A, and why
labs-perplexity 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 2d 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.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/labs-perplexity — Labs Query via Perplexity
Run a query using Perplexity's /labs mode via Playwright browser automation. Similar to /research-perplexity but uses Perplexity's experimental labs mode with a longer 15-minute timeout for complex queries.
No API keys required — uses Perplexity login session only.
CRITICAL: Do NOT ask the user questions before completing Step 0 and Step 1. Compile context silently, build the query, and execute. Only ask questions if $ARGUMENTS is empty AND you cannot determine a useful research focus from the compiled context.
Input
$ARGUMENTS = The research question or topic to investigate. If empty, defaults to a general project analysis.
Workflow
Step 0: Compile Session Context — MANDATORY, SILENT
Before doing ANYTHING else, compile the current session state. Do NOT ask the user any questions during this step — proceed silently and autonomously.
- Read project memory: Read the project's
MEMORY.mdfrom the auto-memory directory to understand what's been worked on, recent patterns, and known issues - Recent commits: Run
git log --oneline -10to see recent work - Uncommitted work: Run
git diff --statto see what's in progress - Active tasks: Check
TaskListfor any active/pending tasks - Synthesize: Form a 1-paragraph internal "current state" summary — do NOT output this to the user, just hold it in context for Step 1
Do NOT present findings. Do NOT ask questions. Proceed directly to Step 0.5.
Step 0.5: Explore Codebase — MANDATORY, SILENT
After compiling session context (Step 0), explore the actual codebase:
- Find key files: Use
Globfor main source files (*.py, *.ts, *.js) in project root and src/ - Read recently modified: Run
git diff --name-only HEAD~5 HEAD, read up to 10 files (first 100 lines each) - Read structural files: README.md, pyproject.toml, package.json if they exist
- Synthesize: Form internal "codebase summary" — key files, purposes, connections
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.
- 2d ago First seen · 142 lines · 0 tokens per session scan A 47188c299f6d
labs-perplexity is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,868 tokens. 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 2026-08-30.
Other commands, from other repositories
hep-browser
Use the Agentlas browser hardpoint for browser-required work.
agentlas-browser
Use the Agentlas browser hardpoint for browser-required work.
auto-verify
프론트엔드 UX 검증 — Playwright 기반 비주얼 검증을 실행합니다.
activate-browser
Activate Chrome DevTools MCP for heavy browser sessions (network inspection, Lighthouse, performance tracing). Deactivate when done.
dial
Live value calibration - 2-4 lettered candidates injected into the running app; click through them against real data, nothing written to source.
interactive-dev
Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.