Vibeweaver并不会让模型变强;它让已有的能力真正发挥作用。

快速开始

重启OpenCode并请求工作;技能触发了实现 / 修改/调试/部署编码任务（不包括问答或纯咨询）。 在请求开头说“严格遵循vibeweaver”会触发你的情绪 基本上是确定的。对于插件、可选附加功能和Windows路径， 参见安装。

验证此版本（w18.3.5 — 默认配置文件：核心）

标签是不可变的。来自标签处的克隆人：

release/MANIFEST.json 通过 SHA-256 绑定每个有效载荷文件，并且 vibeweaver/install.sh 在复制前核实。效果声明保持不变 unverified/directional 直到预注册的G3评估结果到达;否 单次标题作为可靠性声明发布。

为什么它存在

如果人脑可以自由发挥，它就会依赖认知偏差， 事后合理化。科学是我们为此构建的对策： 预注册、盲审、实验笔记本、可重复性。LLM是 同样的机器——在完成图案方面非常出色，同样擅长完成 事后编造理由。

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