plumb /plŭm/ · exactly vertical, true.
Unlock the full potential of Claude Code
Configures Claude around your voice, your guardrails, your context. Built on your machine, in one guided interview.
plumbward-profile.md loaded
voice, guardrails, context
One composed session, not a recording. The dry-run files and ages come from our published eval fixture.
Out of the box, it drifts.
Five failures come up again and again for people who work with Claude every day. Each one has a named fix in the kit.
| The failure | The named fix |
|---|---|
| Deletes and overwrites first, apologizes after. | dry-run Asks for the full list and your approval before anything is deleted, and shows its reasoning per file. |
| Long sessions lose your rules mid-project when context is compacted away. | context-guard Your guardrails live in a checkpoint file and are re-loaded when a new session starts. Machine-enforced in Claude Code. |
| Burns through usage limits re-reading files and padding answers. | token-diet The wasteful habits are named and cut. |
| Writes in fluent AI-brochure voice that you then rewrite by hand. | voice Captured from real samples of your writing, then applied to every draft. |
| Invents plausible-looking citations and states recollection as fact. | verify Separates what was checked from what is recalled, and flags the unchecked, per item. |
Six skills. One profile. Machine enforcement in Claude Code.
Every skill reads a profile written from your answers and your writing. That is what makes the same kit behave differently on your machine than on anyone else's.
setup the interview, this is the product
A guided interview, once. It asks how you work, what Claude must never do without asking, who you write for, and collects real samples of your writing. It writes your profile to your machine (nothing is sent to us) and every other skill reads it from then on. A copied zip without the interview is just text files.
voice
Learns how you write from 3 to 5 real samples: cadence, formality, the words you'd never use. It strips the tells that make text read as generated.
verify
Separates verified from recalled from uncertain, marks each item, and won't print citations it couldn't check.
dry-run
Before anything is deleted, moved, or overwritten: the complete list, oldest-to-newest, traps flagged, and it asks before it acts.
context-guard
Checkpoints long work so a compacted session doesn't silently forget your rules. Resume without a magic phrase.
token-diet
Five ranked cost wins plus a full tactics reference: the habits that quietly burn your usage limits, named and cut.
hooks Claude Code
The enforcement layer: your guardrails are re-injected the moment context is compacted, and destructive commands are gated behind a confirmation. Machine enforcement, not a promise in a text file. It is the one part a copied zip cannot fake.
Interview once. Everything reads it.
Install the kit
Two install paths, a few lines each: upload the .plugin in Cowork or Desktop, or add the marketplace folder in Claude Code.
Say “set up Plumbward”
The interview runs in your own Claude session. It ends by writing
plumbward-profile.md into your working folder: your voice, your
guardrails, your context, in plain text you can read and edit. A redacted sample:
# plumbward-profile.md voice: short sentences · no exclamation points · sign-off "Cheers" never-say: "I hope this finds you well" · "leverage" ·████████guardrails: never delete without the list · never email██████context: agency owner · clients███████████· billing in day rates
Work normally
Every skill reads the profile before it acts. Ask for a draft and it comes back in your voice. Ask for a cleanup and you get the list first. Start a new session and your rules load with it.
What it costs you
Every config kit taxes your context. Ours is published, per skill.
A kit that hides its own overhead is selling you a feeling. These are the CLI's own projections for the installed kit, published as-is, with the unflattering number first, because that's the habit this product is built on.
| context-guard | ~150 always-on · ~1.6k when it fires |
| setup (fires once, ever) | ~100 always-on · ~2.8k at interview |
| verify | ~100 always-on · ~1.6k when it fires |
| voice | ~100 always-on · ~2k when it fires |
| dry-run | ~90 always-on · ~1.5k when it fires |
| token-diet | ~90 always-on · ~1.5k when it fires |
| hooks, the enforcement layer | zero model context |
Projections from claude plugin details, reported verbatim; the CLI qualifies them as estimates. Whether the kit saves more than it costs is a separate question, answered below.
What we've measured, and what we haven't.
This category sells adjectives. We'd rather show you the ledger, including the entries that don't flatter us.
Measured
- That the kit activates unprompted. In our test harness, the kit's skills fired in 20 of 20 sessions where it was installed, and zero where it wasn't, read from the raw session traces.
- The kit's own overhead. ~630 tokens always-on (~196 for the free tier), roughly 1.5k to 2.8k when a skill fires, hooks free. Published above.
- That our test rig is fair. Both test arms ran identical tool surfaces. We threw out an earlier pilot of our own when we found they hadn't.
Not measured, so not claimed
- A token-savings figure. None exists yet. Until it does, no savings number appears anywhere on this page.
- That the kit out-scores a bare model on citation discipline. We ran a 20-topic automated test; it showed no measurable difference, and the per-topic verdicts were noisier than the effect. We're saying so instead of quietly not mentioning it.
- Anyone's productivity multiplier. You will not find an “×” on this page.
Why publish the misses? Because the product's whole premise is that Claude should flag what it can't verify instead of inventing it. A storefront that didn't hold itself to the same rule would be selling something it doesn't practice.
One price. No subscription required.
The paid kit is a one-time purchase with lifetime updates on this version line, and a 14-day no-questions refund.
Lite
Try the two zero-setup skills
$0
free download · no interview needed
- dry-run, asks before anything is deleted
- token-diet, cut the burn
- ~196 tokens always-on
Kit
The full six skills, personalized
$79
one-time · yours for good
- The setup interview: your profile, built from your material
- voice, verify and context-guard, all reading your profile
- dry-run & token-diet, profile-aware
- Hooks enforcement layer (Claude Code)
- Lifetime updates on the v0.2 line
- 14-day no-questions refund
Checkout is opening. Until it does, email and you'll be first in line.
Kit + Room
For teams & heavy daily users
$149
year one · then $59/yr
- Everything in Kit
- Private community
- Monthly config refresh as the platform changes
- Priority support
Not open yet. The kit comes first
The skeptic's corner
Fair questions, straight answers.
Isn't vanilla Claude fine?
For short, low-stakes work, often yes. The kit earns its keep where the defaults fail: long sessions that forget your rules, cleanups that delete before asking, drafts in a voice that isn't yours, citations that were never checked. If none of those have bitten you, you may not need this.
Isn't this all free on GitHub somewhere?
Generic versions of some of it, yes. And our own free tier is real, not crippled: two skills, ~196 tokens always-on, shipping with the public release (the button above will tell you the moment it's out). What you can't download from a list is the interview: the kit's value is created on your machine, from your writing and your rules, when setup runs. A pile of skill files without your profile is the commodity; the profile is the product.
Does it actually work, or is this placebo?
Here's exactly where the evidence stands. Measured: the kit's overhead (published above), and that its skills reliably activate, 20 of 20 installed sessions in our harness, verified from raw traces. Not yet shown: a statistically clean advantage over a bare model in automated scoring. Our first 20-topic test found no measurable difference, and we published that instead of burying it. The mechanism is visible in every session: you get the file list before deletion, the per-item unverified flags, drafts in your captured voice. Whether that's worth $79 is a judgment we'd rather you make with the real numbers in front of you. There's a 14-day refund if you judge wrong.
What do updates cover, and what if Anthropic ships all this natively?
Updates: every update to the v0.2 line is included in the $79, forever: fixes, compatibility work as the platform changes, improvements to the six skills. No renewal, no re-purchase for this line. Whether a future major version costs anything, and what existing buyers get if one ships, isn't decided yet, so we won't promise it here. What you bought keeps working and keeps getting its updates either way.
If the platform absorbs it: possible, platforms do. Two parts are hard to absorb: your profile (it's built from your material, and it's a file you keep), and the interview that builds it. If Claude someday does natively everything the kit does, you'll still have both, and the kit will have been $79, once.
What happens to my data?
Nothing is sent to us. No profile, no writing samples, no sessions. The interview runs inside your own Claude session and writes plumbward-profile.md to your working folder: plain text you can open, edit, or delete. Your conversations with Claude remain governed by your Claude provider's terms, exactly as they are today.
Which Claude products does it work with?
Cowork and Claude Desktop (upload the .plugin file), and the Claude Code CLI (add the bundled marketplace folder). The hooks enforcement layer is Claude Code only; skills work everywhere. Plumbward is an independent product; it works with Claude but isn't affiliated with Anthropic.
What does it not do?
It doesn't make Claude smarter or raise your usage limits. The paid kit's personalization doesn't work without running the interview once, though the two Lite skills run without it. It can't physically prevent every mistake: skills guide the model strongly, and only the Claude Code hooks are hard enforcement. And it won't give you a productivity multiplier, because we haven't measured one.
What if it's not for me?
Email uzayrhai@gmail.com within 14 days for a full refund. No form, no argument. Everything the kit produced from your material stays yours.