Vibeweaver

Vibeweaver doesn’t make a model stronger; it makes the ability already there actually count.

Quickstart

git clone https://github.com/logandoo/vibeweaver
bash vibeweaver/vibeweaver/install.sh   # idempotent; safe to re-run

Restart opencode and ask for the work; the skill triggers on implement / modify / debug / deploy coding tasks (not on Q&A or pure consulting). Saying “strictly follow vibeweaver” at the start of the request makes triggering essentially certain. For the plugins, the optional extras, and the Windows path, see Install.

Verify this release (w19.0 — default profile: core)

Tags are immutable. From a clone at the tag:

python3 scripts/verify_release.py --root .   # MANIFEST OK N/N
sha256sum -c release/MANIFEST.sha256         # corruption only, not replacement
gh attestation verify release/MANIFEST.json --owner logandoo

release/MANIFEST.json binds every payload file by SHA-256 and vibeweaver/install.sh verifies it before copying. Effect claims are directional — the product-form eval (bare 0/9 vs full_deployed 9/9, CI [0.70, 1.0]) is small-sample; no significance claim is published.

Why it exists

Give the human brain free rein and it runs on cognitive bias and after-the-fact rationalization. Science is the countermeasure we built for it: preregistration, blind review, lab notebooks, reproducibility. An LLM is the same kind of machine — brilliant at pattern completion, and just as good at making up its reasoning after the fact.

Vibeweaver puts coding work under the same discipline:

• Acceptance criteria are written before any action and cannot be relaxed mid-loop — preregistration.
• Reviewers and fresh-context verifiers judge the diff and the evidence, never the implementation’s reasoning — blind review.
• Every hypothesis, diagnosis and falsification lands in an on-disk ledger, distilled into memory at task end — the lab notebook.
• Missing evidence blocks delivery mechanically — the publication gate.

None of this ages with model capability. The discipline stays no matter how strong the model gets — even the smartest person still reaches for pen and paper when the reasoning has to hold up.

A coding agent should be able to bring this discipline on its own, but opencode and Codex don’t ship it as a default: they hand you hooks and permissions, and leave the policy to skills and plugins.

Coding agents fail on real projects in familiar ways: they delete files, refactor code nobody asked them to touch, or break feature B while implementing feature A. Most of these are process failures, not capability failures: the agent doesn’t know what “done” means, so it declares victory without proof. It skips the verification it could have run. It forgets what the previous session learned, and drifts over