agentmods.dev

knowledge-index-verify

knowledge-index-verify is a skill for Claude Code, Codex from protect-my-hair/nucleus-marketplace. It costs 39 tokens per session (641 once invoked), scanned A, original, MIT.

A read-only checker for validating a project's documentation index and its supporting evidence. It checks links, feature details, test attribution, and facts gathered from code, then writes a proposed index report under a run-specific folder.

In plain words
What is it for?
Use it to verify documentation and feature metadata, inspect index changes, and produce candidate reports without modifying source code or production documentation.
Why use it?
It catches missing or unsupported documentation evidence before anything is copied into the production knowledge index. It also blocks cases where required code facts are absent.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the nucleus plugin — 27 skills, 1 agent, 1 hook shipped together

not rated 162repo 1mo ago A scan SkillSpector: pass 39 tokens original MIT

Good fit Use it to verify documentation and feature metadata, inspect index changes, and produce candidate reports without modifying source code or production documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/protect-my-hair/nucleus-marketplace/knowledge-index-verify
View source ↗ protect-my-hair/nucleus-marketplace
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 protect-my-hair/nucleus-marketplace --skill knowledge-index-verify
Clone the repo
git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace

Made for: Claude Code, Codex.

Or install nucleus, the plugin that ships this one along with the rest of its 27 skills, 1 agent, 1 hook.

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 knowledge-index-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/knowledge-index-verify/github.svg)](https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/knowledge-index-verify)
Your own site
<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/knowledge-index-verify"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/knowledge-index-verify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for knowledge-index-verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/knowledge-index-verify"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/knowledge-index-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00039 $0.00641
Opus 5 $0.00019 $0.00320
Sonnet 5 $0.00008 $0.00128
Haiku 4.5 $0.00004 $0.00064

Measured 13d ago against content hash b89cf67f94c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

knowledge-index-verify 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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/knowledge_index_verify.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/nucleus/skills/knowledge-index-verify/SKILL.md · 53 lines

What it actually says

knowledge-index-verify

本 Skill 是 Nucleus V2 Knowledge Index / llm-wiki approved-write 的只读 verify gate。它只生成 candidate、diff、report 和 result package，不同步生产索引。

边界

  • 不覆盖 docs/knowledge-index.json。
  • 不生成、更新或补写 docs/features/**/code-facts.md。
  • 不从 LLM prompt、人工摘要或检索结果直接推断代码事实。
  • 不写 docs/requirement/**、docs/features/**、tests/**、.nucleus/tests/** 或源码。
  • Runtime 只允许写 .nucleus/runs/<workflowRunId>/knowledge/** 与 .nucleus/runs/<workflowRunId>/result.json。
  • 失败默认 ALERT_AND_BLOCK，不得静默降级。

使用

python3 skills/knowledge-index-verify/scripts/knowledge_index_verify.py verify \
  --repo-root /path/to/target-repo \
  --context /path/to/target-repo/.nucleus/context/<workflowRunId>.json \
  --tool-evidence /path/to/target-repo/.nucleus/runs/<workflowRunId>/knowledge/tool-evidence/gitnexus-search-report.json

--tool-evidence 必须是显式 adapter evidence JSON。GitNexus、Serena、Yog 或 static analyzer readiness 只能来自该 evidence、capabilityStatus 或工具注册报告，不能凭宿主环境猜测。

Code Facts Strict

当以下任一条件成立时，code-facts 证据缺失必须 FAILED_BLOCKED：

  • docIndexLinks 引用 docs/features/**/code-facts.md。
  • scanner 发现同 feature 目录下存在 code-facts.md。
  • context 明确要求 code facts。

没有 code-facts 的普通 feature 只能进入 candidate-only 与人工 review，不能生成 prompt-only facts。

人审前子代理预审

到达 candidate-index-review 前，必须按 workflow 的 subagentPreReview 调度独立 reviewer 子代理；未取得“材料可提交人工审查”预审结论时，不得请求人工评审通过。

输出

  • .nucleus/runs/<workflowRunId>/knowledge/feature-scan-report.json
  • .nucleus/runs/<workflowRunId>/knowledge/candidate-knowledge-index.json
  • .nucleus/runs/<workflowRunId>/knowledge/index-diff.md
  • .nucleus/runs/<workflowRunId>/knowledge/verify-report.json
  • .nucleus/runs/<workflowRunId>/knowledge/verify-report.md
  • .nucleus/runs/<workflowRunId>/knowledge/blockers.json
  • .nucleus/runs/<workflowRunId>/result.json
Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 53 lines · 39 tokens per session scan A b89cf67f94c3

Subscribe to this mod's changes

knowledge-index-verify is a skill published in the GitHub repository protect-my-hair/nucleus-marketplace (162 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 641 once invoked, about $0.0002 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 2026-08-30.

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens