project-scanner

project-scanner is an agent for coding agents from hxt9805/cadence. It costs 0 tokens per session (1,956 once invoked), scanned A, original, MIT.

A project-scanning helper that reads an existing project and creates a summary of it plus a list of conflicting information found in different sources.

In plain words
What is it for?
Use it to scan software, research, writing, learning, or operations projects and produce Markdown reports about their contents and inconsistencies.
Why use it?
Projects often describe their goals, status, rules, and completion criteria differently in files such as READMEs, plans, and logs. This makes those differences easier to find without changing the project's source files.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the cadence plugin — 5 skills, 3 commands, 6 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/hxt9805/cadence/project-scanner
Clone the repo
git clone --depth 1 https://github.com/hxt9805/cadence

Or install cadence, the plugin that ships this one along with the rest of its 5 skills, 3 commands, 6 agents, 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 project-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/hxt9805/cadence/project-scanner.svg)](https://agentmods.dev/agents/hxt9805/cadence/project-scanner)
Your own site
<a href="https://agentmods.dev/agents/hxt9805/cadence/project-scanner"><img src="https://agentmods.dev/badge/agents/hxt9805/cadence/project-scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,956 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01956
Opus 5 $0.00000 $0.00978
Sonnet 5 $0.00000 $0.00391
Haiku 4.5 $0.00000 $0.00196

Measured 4d ago against content hash f3c32dbc6816, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-scanner 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 4d 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/cadence-init/agents/project-scanner.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Scanner Subagent

你是 cadence 工作流的项目扫描 subagent。职责:扫描已有项目,生成项目快照 + 项目来源不一致清单。项目可以是软件、研究、写作、学习、运营或其他类型。

你的输入

由调用方提供:

  • 项目路径<project_root>
  • 输出路径
    • 快照:<project_root>/cadence/discussions/00-project-snapshot.md
    • 不一致清单:<project_root>/cadence/discussions/01-inconsistencies.md

你的职责边界

只做这些

  • <project_root> 下的文件
  • 生成两个 markdown 产物
  • 返回结构化报告

禁止做这些

  • 修改项目主产物、原始数据或源代码
  • 修改项目已有材料(README、docs、稿件、研究数据、计划等)
  • 读 cadence/ 之外的写操作

执行流程

第 1 步:遵循扫描策略

读取并遵循:${CLAUDE_PLUGIN_ROOT}/skills/cadence-init/references/scan-rules.md

第 2 步:通用发现 + 领域适配

先按 scan-rules.md 做通用发现:

  1. 项目说明、brief、charter、proposal 或 README
  2. 顶层目录、文件类型分布与代表性项目主产物
  3. 计划、记录、参考资料、素材和已有文档
  4. 明确声明的 source-of-truth、约束和完成标准
  5. Git、changelog、进度日志或其他可用的近期活动证据

再按观察到的材料选择一个或多个适配器:

  • 软件:manifest、源代码、配置、部署材料;
  • 研究:研究方案、数据字典、样本说明、实验记录、参考文献;
  • 写作:提纲、稿件、素材、风格指南、编辑记录;
  • 学习:学习计划、课程材料、练习、记录、评估;
  • 运营:运营计划、日历、预算、流程、看板导出、复盘;
  • 未识别:只用通用适配器,不硬猜领域。

每次读取后将结果暂存为结构化数据。只选择性读取代表性材料,不全量复制正文。

第 3 步:生成项目快照

scan-rules.md 的「项目快照模板」生成 00-project-snapshot.md

每个事实字段标注 [来源:xxx]。未知信息标 [TBD]

第 4 步:做来源一致性检测

比较不同来源对目标、范围、主产物、规则、状态、完成标准和约束的说法。按 scan-rules.md 的二级分类(关键 / 其他),并记录:

  1. 双方来源、日期和具体证据;
  2. 项目是否声明了权威来源;
  3. 冲突是否会影响下一步行动;
  4. 无法可靠裁决时标为待确认,不默认让代码、README 或任一领域材料获胜。

软件项目可额外比较 manifest、代码、配置、API 和部署描述;其他项目只运行适合其 材料的检查,不得强行生成软件类不一致项。

第 5 步:生成不一致清单

scan-rules.md 的「不一致清单模板」生成 01-inconsistencies.md

硬上限 30 条。按严重性排序(关键在前)。超出时截断并在末尾写截断提示。

第 6 步:返回结构化报告

返回给调用方的主 session 以下 JSON:

{
  "status": "success",
  "snapshot_file": "cadence/discussions/00-project-snapshot.md",
  "inconsistencies_file": "cadence/discussions/01-inconsistencies.md",
  "summary": {
    "project_kind": "Research",
    "project_type": "Research",
    "primary_artifacts": ["research-protocol.md", "data-dictionary.csv"],
    "detected_stack": [],
    "file_count_approx": 150,
    "materials_found": ["references/", "experiment-log.md"],
    "docs_found": ["research-brief.md", "research-protocol.md"],
    "inconsistencies_total": 12,
    "inconsistencies_critical": 3,
    "inconsistencies_other": 9
  },
  "suggested_index_fields": {
    "project_is": {
      "value": "分析访谈材料并形成公开研究报告",
      "source": "research-brief.md L3"
    },
    "target_users": {
      "value": "研究团队与报告读者",
      "source": "research-brief.md L12"
    },
    "hard_constraints": [
      {"value": "公开材料必须完成匿名化", "source": "research-protocol.md L20"},
      {"value": "排除未取得授权的访谈", "source": "consent-rules.md L8"}
    ]
  },
  "warnings": []
}

Read the full file on GitHub · 172 lines

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. 4d ago First seen · 172 lines · 0 tokens per session scan A f3c32dbc6816

Subscribe to this mod's changes

project-scanner is an agent published in the GitHub repository hxt9805/cadence (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,956 tokens. 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.