Ask Repave from Claude

Repave can answer questions about your features and what they cost from inside Claude, so you do not have to open Repave and read a table to find out where something has got to.

Once connected, you can ask in plain language:

• "What's the status of the checkout feature?"
• "Which features in the CRM project are still unimplemented?"
• "Has the order export feature merged yet?"
• "What's left in the billing module?"
• "What has the CRM project cost so far?"
• "How much did analysing the legacy code cost?"
• "What did we spend on the checkout feature last week?"
• "Which runs were the most expensive this month?"
• "How much did Alice spend in the IDE in September?"
• "How many rounds of implementation has the checkout feature had?"
• "How many prototype revisions did we make on the checkout feature?"

What it can and cannot do

It is read-only. It can list the projects you have access to, list their features, report one feature's progress and history, and report what the AI runs on a project cost and who started them. It cannot change anything, start a job, approve a prototype, or see any project you could not already open yourself.

You connect once, per person. What Claude can see is exactly what you can see when you sign in — connecting does not grant access to anything new, and it does not let anyone else read your projects.

Connect Claude Desktop

1. In Repave, open the account menu in the top right and choose Connected apps.
2. Copy the connector URL shown under Connect a new app.
3. In Claude Desktop, go to Settings → Connectors → Add custom connector.
4. Paste the URL and choose Add.
5. A browser window opens on Repave. Sign in if you are asked to, then choose Allow.

That is the whole setup. There is no token to copy, no configuration file to edit, and you will not be asked to sign in again.

Connect Claude Code

Run this once, using the connector URL from Connected apps:

claude mcp add --transport http repave <connector-url>

Then run /mcp, choose repave, and choose Authenticate. A browser opens on the same consent screen; choose Allow.

What you get back

Asking about one feature returns its position in the Repave pipeline, in order:

Stage	What it means
As-Is	The legacy behaviour has been captured as scenarios.
To-Be	The specification for the new system has been written.
Prototype	A UI prototype exists, with its version and whether it is approved.
Implemented	How many scenarios an agent has written code for.
Verified	How many scenarios a test run has actually seen pass.
Pull request	Whether a pull request is open, merged, or closed.
Merged	Whether the work reached a branch, and which one.

Implemented and verified are deliberately separate. "Implemented" is the agent's own report that it wrote the code. "Verified" is a test run's observation that the code passes. A feature can be fully implemented and not yet verified, and the two are never reported as one number.

Some stages report not applicable rather than outstanding. A batch job project has no user interface, so it has no prototype stage; a feature that did not go through user acceptance testing has nothing recorded for verification.

Costs

Cost answers use the same figures as the project's Costs page, so the two always agree. Anyone who can open a project can ask what it cost; connecting grants nothing extra.

You can ask for:

Question	What comes back
A project's cost	The total, the split by pipeline stage, by model and by person, what legacy analysis cost, the most expensive features, and spend that belongs to no single feature.
A feature's cost	Its total by stage, by model and by person, next to its status, and the cost per To-Be scenario.
Spend over time	Spend per day or per week, for a project, one feature, one stage or one person, over any date range — for example one person's Repave IDE spend per week.
Individual runs	Each AI run with its cost, model, tokens and who started it, filtered by feature, person, stage, legacy analysis or date, newest or most expensive first.

Dates are in UTC, weeks start on Monday, and amounts are in US dollars.

Estimated and unknown costs are reported as such. Some providers do not report what a run cost, so Repave estimates it from the provider's published prices; those amounts are marked estimated. If a model has no published price, the run's cost is unknown rather than zero, and it is counted separately so it is never mistaken for a free run.

Legacy analysis is the work of reading the legacy code: discovering its features, capturing its current behaviour as scenarios, and extracting its architecture and data. It is reported as its own figure, and it is part of the Other stage rather than added on top of it, so the stages always add up to the total.

When a list of runs is cut short, the totals still cover every run that matched, so a figure is never a sum of only the runs that were shown.

Spend by person

Every run is attributed to the person who started it: who chose Implement or Retry, who executed an implementation plan, who asked for a prototype, or who opened the Repave IDE session. Spend in an IDE session that several people joined counts toward the person who opened it.

Some runs have no person — work Repave started on its own, and runs from before Repave recorded who started each one. These are reported as unattributed, never dropped or shared out, so the amounts per person and the unattributed amount always add up to the total.

Only the project owner sees other people's spend. Anyone else who asks for a split by person sees their own spend and everyone else's combined into one figure, and is told so if they ask about someone else by name. The same applies to a feature's history: someone else's round or revision is shown without their name. The project's Costs page does not show spend by person.

A feature's history

Ask how many rounds a feature took and you get:

Part	What counts as one
Implementation rounds	Each time someone chose Implement or Retry on the feature, with who started it, how it ended, its preflight rounds, how many times the agent re-ran its own checks, and what it cost. A module run counts as a round on every feature in the module; its cost is shown for the whole module, because it cannot be split fairly between them.
Preflight rounds	Each round of questions preflight asked, with how many were answered and how many abandoned. Answers carried over from an earlier attempt are not a new round.
Prototype revisions	Each prototype request: generating designs, adding options, updating one option, refining, acting on review comments, upgrading an option, or pulling from Figma, with who asked, whether it succeeded, and what it cost.

The prototype's version number counts changes to the chosen design, not requests, so it is reported separately and is not the number of revisions. Spend on the feature outside these rounds — writing its To-Be scenarios, Repave IDE sessions, review — is reported as one figure, so everything adds up to the feature's cost.

Naming a project or feature

You do not need identifiers. "The checkout feature" is enough. If more than one feature matches what you asked for, Claude is told which ones matched and will ask you which you meant rather than guessing.

Disconnecting

Open Connected apps and choose Revoke next to the app. Access stops immediately — the next thing that app tries to read is refused. You can connect it again later at any time.

The same page lists every app you have connected, when you connected it, and when it was last used, so you can tell at a glance whether a connection is still being used before you remove it.

If the connector will not connect

Claude Desktop and Claude Code connect from your own computer, so they can reach a Repave installation on your company network or VPN.

Claude in a web browser is different: it connects from Anthropic's servers, which have to be able to reach your Repave installation over the public internet. If your installation is on an internal network, behind a VPN, or has no inbound internet access, use Claude Desktop instead.