Skip to content
Agentmart
Submit a tool

ibl-access

Use this skill when a task needs IBL data access setup, ONE/Alyx authentication, or selecting between public and private data modes.

Skill by int-brain-lab

IndexedMIT★ 54
Write a review

Chalk Labs

Need help deploying ibl-access?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/int-brain-lab-ibl-access

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use this skill when a task needs IBL data access setup, ONE/Alyx authentication, or selecting between public and private data modes.

Use cases: data, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ibl-access

What's inside

Skill name
ibl-access
Description
Use this skill when a task needs IBL data access setup, ONE/Alyx authentication, or selecting between public and private data modes.
License
MIT
Instructions
43 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • one_auth.md · references/
  • session_search.md · references/

SKILL.md (first lines)

# IBL Access

## Use this skill when
- You need to connect to IBL data via ONE.
- You need to switch between `public` and `private` access modes.
- You need session/insertion queries constrained by releases/tags.

## Local references (read before browsing)
- `../SOURCES.md`: provenance index for this skill and its references.
- `references/one_auth.md`: ONE instantiation, online/offline modes, auth patterns.
- `references/session_search.md`: `search`, `search_terms`, `search_insertions`, and Alyx REST patterns.

Default policy: use these local references first. Browse official docs only when behavior differs from references or an API call fails unexpectedly.

## Workflow
1. Check `IBL_AGENT_DATA_OFFLINE`; if it is `1`, follow Offline mode below. Otherwise, determine mode (`public` or `private`) and record it in run metadata.
2. Configure ONE base URL:
- Public: `https://openalyx.internationalbrainlab.org`
- Private: `https://alyx.internationalbrainlab.org`
3. Validate auth state:
- interactive login path,
- non-interactive env path.
4. Build query strategy with performance defaults:
- narrow filters first,
- `limit`/`offset` paging for large pulls,
- `details=True` only when needed,
- `query_type="local"` vs `"remote"` selected explicitly.
5. Return connection status and provenance fields required by profile reports.

## Data-offline mode (`IBL_AGENT_DATA_OFFLINE=1`)
- Perform cache-only loading with `one.api.One(cache_dir=...)`. Do not use `one.api.ONE(...)`.
- Do not use `mode="remote"`, `cache_rest`, or `no_cache=True` as these all reach Alyx.
- `connect_one()` raises `OfflineModeError` under this flag; construct `one.api.One(cache_dir=...)` directly.
- Searches and loads only see what is already in the cache. If a dataset is absent, report it as missing and ask the user to provide it - do not trigger a download.
- Record offline mode and the cache root in the provenance block.

## Outputs
- Resolved endpoint.
- Auth mode used.
- Query constraints (release/tag/session filters).
- Provenance block for reports.

From int-brain-lab/ibl-ai-agent, MIT.

More from int-brain-lab/ibl-ai-agent

Signals

Stars
54
Forks
16
Open issues
10
Last commit (this folder)
Oct 1, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from int-brain-lab

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ibl-access running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ibl-access?

CallGet help
Cite this page

ibl-access skill. Agent Mart. https://agentmart.dev/skills/int-brain-lab-ibl-access (last updated 2026-10-24)