Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chentao326/vibe-code --skill vibe-assessgit clone --depth 1 https://github.com/chentao326/vibe-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chentao326/vibe-code/vibe-assess)<a href="https://agentmods.dev/skills/chentao326/vibe-code/vibe-assess"><img src="https://agentmods.dev/badge/skills/chentao326/vibe-code/vibe-assess.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.02165 |
| Opus 5 | $0.00049 | $0.01082 |
| Sonnet 5 | $0.00020 | $0.00433 |
| Haiku 4.5 | $0.00010 | $0.00216 |
Grade A, and why
vibe-assess scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-assess — 任务评估 + 盲预估
核心流程:读任务 → 委派盲打分 → 写预估指标 → 用户 review → 落盘。
严格遵守 blind-prediction-protocol.md。 完整组件见 task-assessment-anatomy.md。
Overview
Phase 0: Blind check 自检
Phase 0.1: Handoff phase check(融合)
Phase 0.5: 解析输入路径
Phase 1: 读 task + rubric + state
Phase 2: 委派盲打分 sub-agent(Task tool)
Phase 2.5: Disagreement detection + 用户裁定
Phase 3: 写预估指标(耗时/轮次/bug风险/概率分布)
Phase 4: 写关键假设
Phase 5: 用户 review
Phase 6: 落盘 + 更新 state
Constants
- BLIND_CHECK = strict
- BLIND_SCORING = on(默认)——走 blind sub-agent
- DISAGREEMENT_THRESHOLD = 2——|Δ| ≥ 此值弹用户裁定
Workflow
Phase 0: Blind check 自检
按 blind-prediction-protocol.md 自检:
- 任务是否已开始编码?→ 是 → 拒绝
- 对话里是否提到任何执行结果?→ 是 → 拒绝
- 通过 → 继续
Phase 0.1: Handoff phase check(融合协议)
根据 handoff-vibe-bridge.md 检测当前 handoff 阶段:
ls handoff/*.json 2>/dev/null || echo "NO_FILES"
| handoff 状态 | 处理 |
|---|---|
handoff/plan-ready.json 存在 |
拒绝——spec 和 plan 已完成,评估已不盲。提示用户走 vibe-retro |
handoff/build-done.json 存在 |
拒绝——编码已执行,数据已泄露 |
handoff/ 有其他信号文件 |
警告 + 标注 handoff_mid_cycle: true + 继续 |
handoff/ 为空 |
✅ 通过——可以评估。完成后提示"可以开始写 spec,说'交接'启动 handoff" |
Phase 0.5: 解析输入路径
用户给的路径应是 tasks/<date>_<id>_<short>.md。
| 形态 | 处理 |
|---|---|
tasks/<file>.md |
标准路径,直接用 |
| 外部 .md 文件 | 建议 cp 到 tasks/ 管理 |
| 纯文本(无文件) | 帮用户创建 tasks/.md |
如 task 文件不存在 → 报错。
Phase 1: 读取输入
- 读
tasks/<id>.md全文 - 计算
task_hash = sha256(task 内容)[:12] - 读
.vibe-state.json拿rubric_version、calibration_samples、project_type、primary_language - 从
calibration_samples派生 confidence 等级(见 task-assessment-anatomy.md) - 读
rubric.md识别当前公式 + 维度
Phase 2: 委派盲打分 sub-agent
BLIND_SCORING=on(默认)——通过 Task tool spawn 一个 context-isolated sub-agent。
Task prompt 必须精简,仅含:
Spawn blind assessor sub-agent.
Input:
task_path: tasks/<date>_<id>_<short>.md
rubric_path: rubric.md
Task: 按 rubric.md 当前公式给上面 task 打分。返回严格 JSON:
{
"dimensions": {
"CS": {"score": 0-5, "confidence": "low|medium|high", "reason": "..."},
"CX": ...,
"AM": ...,
"TE": ...,
"AQ": ...
},
"composite": X.XX,
"input_status": {
"rubric_read": true,
"task_read": true,
"any_other_file_read": false
},
"self_check": {
"saw_execution_data": false,
"any_contamination_signal": false
},
"refusal": null
}
不要读 .vibe-state.json / predictions/ / retros/ 任何其他文件。
不要询问用户——你没有用户。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 209 lines · 99 tokens per session scan A 15b883b64d00
vibe-assess is a skill published in the GitHub repository chentao326/vibe-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 2,165 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…