vibe-score-blind

vibe-score-blind is a skill for Claude Code from chentao326/vibe-code. It costs 77 tokens per session (628 once invoked), scanned A, original, MIT.

An internal helper for scoring coding tasks against a five-part rubric without seeing execution results or other evaluation data. A rubric is a set of scoring rules.

In plain words
What is it for?
Use it only as a sub-agent called by the related assessment tools to produce strict JSON scores, confidence levels, and reasons from a task and rubric.
Why use it?
Keeping the scorer separate from implementation results helps reduce bias in the assessment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit Use it only as a sub-agent called by the related assessment tools to produce strict JSON scores, confidence levels, and reasons from a task and rubric.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chentao326/vibe-code/vibe-score-blind
Install

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.

Any agent
npx skills add chentao326/vibe-code --skill vibe-score-blind
Clone the repo
git clone --depth 1 https://github.com/chentao326/vibe-code

Made for: Claude Code.

Wrote 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.

agentmods badge for vibe-score-blind

README.md
[![agentmods](https://agentmods.dev/badge/skills/chentao326/vibe-code/vibe-score-blind.svg)](https://agentmods.dev/skills/chentao326/vibe-code/vibe-score-blind)
Your own site
<a href="https://agentmods.dev/skills/chentao326/vibe-code/vibe-score-blind"><img src="https://agentmods.dev/badge/skills/chentao326/vibe-code/vibe-score-blind.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.00628
Opus 5 $0.00039 $0.00314
Sonnet 5 $0.00015 $0.00126
Haiku 4.5 $0.00008 $0.00063

Measured 7d ago against content hash 7e1e68d859a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vibe-score-blind 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.

skills/vibe-score-blind/SKILL.md · 63 lines

What it actually says

vibe-score-blind — Channel B (blind scorer sub-agent)

⚠️ 子 agent,非用户 skill。只能由 vibe-assess / vibe-bump 通过 Task tool spawn。

Why this exists

主 AI 看过 git log、执行结果、历史复盘。inline 打分 = 被污染。Channel B 用全新 context——只看 task + rubric.md。

Inputs(白名单)

必填 说明
<task-path> tasks/.md 全文
<rubric-path> rubric.md 当前公式

仅此两个文件可读。

禁读(hard list)

路径 refusal_code
.vibe-state.json blocked_contaminated_input
predictions/*.md blocked_contaminated_input
retros/*/ blocked_contaminated_input
codebase-profile.md blocked_profile
含"实际/耗时/完成/diff/lint/bug"的文件 blocked_contaminated_input

Output(严格 JSON)

{
  "dimensions": {
    "CS": {"score":4,"confidence":"high","reason":"文件路径和期望行为都写了"},
    "CX": {"score":2,"confidence":"high","reason":"仅涉及auth模块"},
    "AM": {"score":1,"confidence":"high","reason":"信息完整"},
    "TE": {"score":4,"confidence":"medium","reason":"有测试但验收标准偏主观"},
    "AQ": {"score":5,"confidence":"high","reason":"代码修复AI强项"}
  },
  "composite": 6.4,
  "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
}

主 AI 调用契约

Task prompt 仅含:

Spawn blind assessor sub-agent.
Input: task_path=<path>, rubric_path=rubric.md
Task: 按 rubric.md 打分。返回严格 JSON。不要读 state/predictions/retros。不要询问用户。

调用前自检:grep -Ei '实际|耗时|完成|diff|lint|bug|过去|上次'

Changes

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.

  1. 7d ago First seen · 63 lines · 0 tokens per session scan A 7e1e68d859a0

Subscribe to this mod's changes

vibe-score-blind is a skill published in the GitHub repository chentao326/vibe-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 628 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens

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…

openai/codex · 114 tokens