Execute Right — Development skill for Claude Code
A Claude Code skill for the moment a plan is carried out: a handed value is a hypothesis, a done-claim names its check, and a controller's rules for running a plan through subagents.
How to install Execute Right
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lumi-fiona/execute-right and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Execute Right does
A Claude Code skill for the moment a plan is carried out: a handed value is a hypothesis, a done-claim names its check, and a controller's rules for running a plan through subagents. Pairs with plan-hard.
Alternatives in Development
- Product Name — Brainstorm 5 memorable product names aligned to brand values 7.8k ★
- Ideation — Ideation — Literature Search & Hypothesis Generation 613 ★
- ExportProfile — Generate a complete personal profile summary of everything you know about me from our conversations 250 ★
README
execute-right
A Claude Code skill for the moment a plan is about to be carried out.
[`plan-hard`](https://github.com/lumi-fiona/plan-hard) governs what a plan may **claim**. This governs what an executor may **trust** — and, since 2026-09-02, what a controller does while running that plan through subagents.
Install
Clone it into your skills folder. Claude Code picks it up by the description in `SKILL.md`; nothing else to configure.
git clone https://github.com/lumi-fiona/execute-right.git ~/.claude/skills/execute-rightTo update, `git pull` in that folder.
What it says
- A handed value is a hypothesis. An exact constant, width, timeout or selector in a step is the author's estimate until you have run the thing that produces the real one. Measure, then type — and report a deviation with the measurement that justified it.
- A done-claim names its check. The command, probe or diff that could have failed. "Tests pass" means the project's own test command, not a file run directly. A check whose passing state looks identical to its not-having-run state proved nothing.
- Stop conditions are honored. A step that names a failing number and gets one halts there. It does not get argued into the value you found.
- Who runs this comes from measurements, not vibes. Read the model/effort stamp on the step; without one, route from your own measured notes and name an unmeasured config as unmeasured.
- When you are the controller. The plan's Global Constraints go verbatim into every implementer and reviewer prompt; the File map decides what may run at once and keeps one writer per file; a step that spends money or deploys is yours, and its measured result is what the next reviewer sees; a reviewer gets the numbered ways this diff could be wrong, never "review this"; ambiguity is pre-resolved, never left as a question a background agent cannot ask; a fix is proved by reverting it and watching its test go red; the ledger of accepted
Related Skills
Brotherme Stop
Stop the Full-Auto controller run right now, draining in-flight work and releasing every held claim
Stingray
A Claude Code Stop hook for the turn that ends half-done — nothing done, an announced action never carried out
PM Claude Brief
CLAUDE.md templates and brief-writing discipline for product managers. Hypothesis-first, evidence-required, sh
Brotherme Auto Status
Show where the Full-Auto controller run stands right now, in plain language
Market Product
Brainstorm marketing ideas, positioning, value prop statements, and product names — creative marketing toolkit
Number Roll
Number roll. Digits roll to a new value like a counter, right-most digit first, while colons, commas and lette
Related Agents
Dx Triggering Reviewer
Review description and triggering quality plus developer experience: would the model route to this artifact at
Namer
Invents a name for a persona that has none, so the others at the table can address them. Reads nothing and wri
What Breaks
Opus 5 validator that pressure-tests a handed artifact — diff, PR, document, design, claim, or question — and
