Architecture review
A written assessment of a subsystem from a Plan-mode pass, with the trade-offs it found rather than a verdict.
For the team
Stop being the routing layer.
Status lives in your head, assembled from five conversations, and the same three questions arrive every week. Now the team puts them to the code directly, in the channel it already works in.
For engineering managers
The wait today
Being the routing layer is most of the job and none of the title. The answers exist — in the branch history, in the review queue, in the modules that keep coming back — but assembling them costs a morning, so they get assembled weekly at best and carried in your head in between.
They ask
Ask in your own words. The answer names its commit.
Mention @PRCHD with the question you’d have saved for a colleague, and it reaches the agent exactly as typed. The agent reads the project’s checkout in Act mode, which changes nothing on disk, and the answer lands in the thread footed with the commit it was read from.
- @PRCHD what’s changed on main since Friday, and what’s risky in it?
- @PRCHD which parts of this repo have no tests and change most often?
- @PRCHD summarise the open PRs — which are waiting on a decision rather than a review?
- @PRCHD we keep breaking checkout. what’s structurally wrong with that module?
They run
The jobs that keep coming back, written down once.
Each is a prompt plus a posture that someone on the team writes once. After that, anyone in a private channel the operator enabled for runs starts it with one slash command, and the result comes back in the thread. These are examples for engineering managers, not a catalog to install — PRCHD supplies the engine, and each team writes its own.
Dependency and upgrade audit
What is behind, what is a security bump, and what would break at the call sites.
Test-gap report
Coverage of the modules that actually change, not the average across the repository.
Onboarding brief
A tour of a subsystem written for one new hire’s background.
Scheduled and triggered
Some of the work is done before anyone asks.
Put the same recipe on a cron line or behind a webhook URL and it starts on its own, so work that used to wait for someone to wake up or find time is already done when people arrive.
- A nightly needs-a-human digest of the work that stopped, and why it stopped.
- A weekly review-latency report — which PRs waited, and on whom.
- A recurring dead-code and TODO-debt sweep.
What changes
The status an engineering manager currently assembles by asking five people assembles itself.
Where it stops. PRCHD reports token and context usage, not money, so a budget figure comes from the team’s own model accounts. It drives the agent CLIs the team already signs in to, and resells no model access.
Other roles
The same host answers the rest of the team.
Product managers
@PRCHD is the export limit still 500 rows, and where is it enforced?
Product questions get answered from the code, without booking an engineer.
Founders and CTOs
@PRCHD how hard would it be to support a second currency?
Leadership gets ground truth directly, at 22:00, without pulling anyone off anything.
Support and QA
@PRCHD a customer says CSV export drops the last row — is that possible in the current code?
The first-line answer comes from the code, names its commit, and takes a minute.
Where your code lives
The computer you own is the computer that runs.
Repositories, worktrees, prompts, transcripts, diffs, command output, attachments, environment values, and the event log stay on the computer you installed PRCHD on — the one that already has your code and your tools. The agent works there, so there is nothing to copy into a hosted environment and nothing uploaded to be indexed.
One small public service handles what a computer with no open port can’t do on its own: it enrolls your computer’s identity, forwards short push notifications, and holds webhook deliveries until your computer collects them. Each delivery is sealed to your computer’s public key the moment it arrives, so the service only ever holds ciphertext, and it is never in the path of your work.
Standing watch
Send this to whoever runs the shared computer.
One person installs it — an afternoon, not a migration. Everyone else asks from a Slack channel they’re already in, and nobody creates an account, installs an app, or pairs a phone.