agentmods.dev

ensure-space

A command that files the current Perplexity research thread into a Space, which is Perplexity's named area for organizing related conversations. It creates the Space when needed.

In plain words
What is it for?
Use it from an open Perplexity thread to save the conversation under a project name, optionally supplying a different Space name.
Why use it?
It keeps research associated with the active project without requiring you to manually choose or create a Space.

Command

57 9d ago A scan 0 tokens original MIT
View the source file intellegix/intellegix-code-agent-toolkit
Install

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.

agentmods
npx agentmods add commands/intellegix/intellegix-code-agent-toolkit/ensure-space
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00373
Opus 5 $0.00000 $0.00187
Sonnet 5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00037

Measured 2d ago against content hash d8061fb71cde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ensure-space 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.

commands/ensure-space.md · 37 lines

What it actually says

/ensure-space — Add Current Perplexity Thread to Project Space

Ensure the current Perplexity thread is filed into a Space named after the active project. Creates the Space if it doesn't exist.

Prerequisites: Perplexity Max subscription. Browser-bridge MCP server running with Chrome extension connected. Active tab must be on a Perplexity thread page.

Input

$ARGUMENTS = Optional space name override. If empty, derives from current working directory.

Workflow

Step 1: Determine Space Name

  • If $ARGUMENTS is provided and non-empty, use it as the space name
  • Otherwise, derive from the current working directory: use path.basename(process.cwd()) (e.g., "my-project")

Step 2: Add to Space

  • Call browser_add_to_space with:
    • spaceName: the determined space name
    • createIfMissing: true

Step 3: Report Result

Based on the response:

  • action: 'added' → Report: "Thread added to Space: {spaceName}"
  • action: 'created' → Report: "Created new Space '{spaceName}' and added thread"
  • action: 'no_match' with createIfMissing failure → Show available spaces, ask user to pick one or confirm creation
  • Error (MENU_NOT_FOUND, ADD_TO_SPACE_NOT_FOUND, MODAL_NOT_FOUND) → Report the error and suggest the user check they're on a Perplexity thread page

Error Handling

  • If no browser tab is active or not on Perplexity, report clearly
  • Do NOT call browser_close_session — this command operates on an existing tab, not a full session
Changes

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.

  1. 2d ago First seen · 37 lines · 0 tokens per session scan A d8061fb71cde

Subscribe to this mod's changes

ensure-space 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 373 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.

Project managementagentic-aiai-agentsanthropicautomationclaudeclaude-code
Related

Other commands, from other repositories

projects

View your Claude Code projects tracked by EverMem.

EverMind-AI/EverOS · 9 tokens

session-cleanup

Tidy your Sessions board -- fix each session's phase, mark finished work complete, and flag old sessions to archive.

nimbalyst/nimbalyst · 23 tokens

track

Create a tracking item in the Nimbalyst tracker system.

nimbalyst/nimbalyst · 12 tokens

checkpoint

Export, refresh, verify, or import a comprehensive cross-topic Project Knowledge Checkpoint for a repository, with privacy checks.

nvk/llm-wiki · 24 tokens

speckit.tasks

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

caipe-io/ai-platform-engineering · 18 tokens

portfolio

Show a read-only hub-wide portfolio of canonical Ideas and active Projects without duplicating topic-owned records.

nvk/llm-wiki · 20 tokens