What Claude and ChatGPT can do with CodeHerder

A connector is a live link from claude.ai or chatgpt.com to CodeHerder, using your own account and your own permissions — connecting one never gives Claude or ChatGPT any access you don’t already have. If you can’t see a workspace, a task, or a piece of team memory in the CodeHerder app, the connector can’t see it either.

This page describes what each capability actually does. For the click-by-click steps to add the connector itself, see Connect CodeHerder to claude.ai or ChatGPT.

What it can do

Read

See your workspaces. Lists every CodeHerder workspace you’re a member of, or checks whether you have access to one specific workspace.

Say something like: “What CodeHerder workspaces do I have access to?”

List tasks. Shows tasks in a workspace, including its sub-workspaces. By default this only shows open work (not-yet-started and in-progress tasks) — ask for completed tasks explicitly if you want those too.

Say something like: “What are my open tasks in the Marketing workspace?” or “Show me the tasks that are done.”

Read one task in full. Pulls up everything about a single task: its title, description, status, priority, and — once an agent has run automated checks against it — the results of those checks.

Say something like: “Give me the full details on task abc-123.”

Read a task’s comments. Shows the discussion thread on a task, newest first.

Say something like: “What’s the latest discussion on that task?”

Read recent activity. Shows a feed of what’s happened recently — your own activity, everything in a workspace, or everything on one specific task.

Say something like: “What’s happened on this task recently?” or “What have I been up to in CodeHerder today?”

Read the team’s workspace memory. Your team can save durable notes, conventions, and context in CodeHerder (“workspace memory”) so agents and teammates don’t have to relearn the same things. Claude/ChatGPT can list what’s there and read one entry in full. You’ll only ever see memory shared with the whole team — not another teammate’s private notes.

Say something like: “What does our team’s CodeHerder memory say about deploy conventions?”

Write

Create a task. Creates a new task in a workspace, following that workspace’s own task rules (what task types it allows, what priorities are valid, and so on).

Say something like: “Create a task in the Backend workspace called ‘Fix the flaky login test’.”

Comment on a task. Posts a comment on an existing task — the same as posting one in the app. Anyone mentioned in the comment gets notified, people watching the task get notified, and if an agent is actively working on that task, it gets woken up to see the new comment.

Say something like: “Add a comment to task abc-123 saying the fix is ready for review.”

What it cannot do

The connector is deliberately limited to reading and to the two actions above. It cannot:

• Start, stop, or otherwise drive an agent session or sandbox
• Change a task’s status or move it through its workflow
• Edit a workspace’s task types or workflow rules
• See another person’s or agent’s private memory
• See any workspace you are not a member of

Read-only vs read-and-write access

Connecting from claude.ai or chatgpt.com the normal way sets the connector up with both read and write access — the create-task and comment actions above work right away, with no extra prompt to grant them.

The one case where writes are refused is a connector whose underlying credential was deliberately set up as read-only — something an admin does for an advanced or self-hosted setup, not part of the ordinary claude.ai/chatgpt.com connect flow. If you hit that, reconnecting won’t change anything; ask whoever set up the connector to switch it to read-and-write instead.

Limits you may notice

• Long lists come back a page at a time. If a workspace has a lot of tasks or a task has a lot of comments, you’ll get the first batch — just ask for the next page (e.g. “show me more”) and Claude/ChatGPT will fetch it.
• Team memory has a cap. Only a bounded number of memory entries are recalled at once; if your team has saved a lot, you may be told the list was cut off.
• A burst of requests can be rate-limited briefly. If you (or an automation) fire off a lot of CodeHerder requests in a short window, you may see a brief “too many requests” message — it clears on its own within a minute.

If something goes wrong

• You’re asked to sign in every time, instead of staying connected. Your connector’s credential likely expired — reconnecting refreshes it.
• You get “not found” for a task or workspace you can clearly see in the CodeHerder app. You’re probably signed into a different CodeHerder account, or the item belongs to a workspace you’re not a member of under that account. Check which account the connector is signed in as.
• A create-task or comment request is refused. This connector’s credential was set up as read-only (see “Read-only vs read-and-write access” above) — that’s not something a normal claude.ai/chatgpt.com connection does on its own, so ask whoever set up the connector to switch it to read-and-write.
• Tools stop being offered partway through a ChatGPT conversation, even though the connector is still listed as connected. This is a known ChatGPT-side issue, not a CodeHerder problem — start a new chat and it should work again.

For the click-path to add or remove the connector itself, see Connect CodeHerder to claude.ai or ChatGPT.