Buy vs build gain
Skill stdin/buy-vs-build/plugins/buy-vs-build/skills/buy-vs-build-gain
Stop AI coding agents from adding dependency and build ownership without a decision note.
npx -y skills add stdin/buy-vs-build --skill buy-vs-build-gainAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when summarizing Buy vs Build benchmark cases, behavior measurements, expected impact, release notes, or evidence that the ruleset reduces unnecessary code, dependencies, cost, or ownership risk.
SKILL.md
1.1 KB, as published. Nobody here has run it
Buy vs Build Gain
Summarize impact from benchmark data without overstating it. Distinguish measured local overhead from behavior benchmarks that still need agent runs.
Workflow
- Read
benchmarks/behavior-cases.jsonfor behavioral test cases. - Run
npm run benchmarkfor local instruction and hook overhead. - If agent-run results exist, report LOC, files changed, dependencies added, decision-note quality, time, token/cost data, and safety regressions.
- If only cases exist, call them a benchmark plan, not measured impact.
Output
Use this shape:
Measured
- <metric>: <value>
Behavior cases
- <case>: expected rung <rung>; baseline risk <risk>
Limitations
- <what has not been measured yet>
Never claim the ruleset reduces LOC, cost, or time until a baseline-vs-enabled agent run has actually been measured.