Borrowing it
Nothing to install: this file belongs to elwsls/verifiable-claim-seed. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elwsls/verifiable-claim-seed/main/CLAUDE.mdgit clone --depth 1 https://github.com/elwsls/verifiable-claim-seedWrote 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/instructions/elwsls/verifiable-claim-seed/claude-md)<a href="https://agentmods.dev/instructions/elwsls/verifiable-claim-seed/claude-md"><img src="https://agentmods.dev/badge/instructions/elwsls/verifiable-claim-seed/claude-md/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.
<a href="https://agentmods.dev/instructions/elwsls/verifiable-claim-seed/claude-md"><img src="https://agentmods.dev/badge/instructions/elwsls/verifiable-claim-seed/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01173 | $0.01173 |
| Opus 5 | $0.00587 | $0.00587 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
verifiable-claim-seed CLAUDE.md 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 9d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verifiable-claim-seed — CLAUDE.md
Machine-checkable claim contract + zero-dependency gate + real samples. 核心命题:可复现≠可验证 (reproducible≠verifiable) —— repro+frozen/snapshot 只证内部一致性;外部正确性由 anchor 承担。PASS 永远带着影子出厂:doubt 表面 + stage 方向相位。
Agent-first entry
- 先读
ai-catalog.json(机器可读清单,含全部概念与入口)→ 再读本文件 →llms.txt补充。 - 跑
python3 verifiable_claim_seed/verify_claim.py self-test确认门禁自检全绿(当前 49 例),再动任何东西。
Commands
python3 verifiable_claim_seed/verify_claim.py self-test # gate 自检(49 cases,须全绿才动手)
python3 verifiable_claim_seed/verify_claim.py verify <claim.json> [--report out.json]
python3 verifiable_claim_seed/mcp_agent_sim.py # 模拟陌生 agent 走 MCP 全链路(8 cases)
verify-claim self-test # pip install verifiable-claim-seed 后
退出码:0 全过 / 1 硬失败(结构/格式/声明引用的文件缺失) / 2 用法·环境 / 3 证据契约违规(哈希失配/复现不符/引用句不在快照)。
Architecture(字段即契约,无散文歧义)
verifiable_claim_seed/schema/verifiable-claim-v1.schema.json— 声明契约规格(JSON Schema 2020-12,additionalProperties:false,tier 规则在 allOf)。verifiable_claim_seed/verify_claim.py— 实际校验器(纯 stdlib,不依赖 jsonschema)。schema 与 gate 是平行实现;self-test的「schema-gate 契约同步」例机器核验两者不漂移(字段/枚举/required 列表/嵌套白名单)。- 三份真实声明:
verifiable_claim_seed/claims/VC-20260815-001.json(ISS 轨道高度,derived + frozen + repro)·VC-20260823-001/002(1 万步,primary + text-quote 锚 + 源快照)。 - MCP server:
verifiable_claim_seed/mcp_server.py(stdio,零依赖;tools:self_test / validate / verify-with-allow_execution)。 - MCP 模拟 agent:
verifiable_claim_seed/mcp_agent_sim.py——以 subprocess 走完整 MCP 链路,验证陌生 agent 发现→决策→调用零人工可用(8 cases)。
硬规则(每次改动)
- self-test 须先绿再改,改后必绿:任何新行为必须加自检用例。
- schema-gate 同步守卫:改 schema 的字段/枚举/required 必须镜像到
verify_claim.py常量(SCHEMA_FIELDS/*_FIELDS/*_REQUIRED/TEXT_QUOTE_REQUIRED),否则自检的漂移守卫失败。 - 每改必 commit;删除用
trash,禁rm。
设计边界(动手前必读,都是故意的)
- 无沙箱:
verify以 subprocess 真实执行repro.script(120s 超时)——只验证你信任的声明;验证来源不受信的声明等于在本机执行其任意代码。 - 路径语义:声明内
data//scripts/路径相对包根解析,非相对声明 JSON。拷单文件声明到别处即断。 - repro.script 必须为 Python(sys.executable 执行);shell/其他语言会被当失败脚本误报。
- 设计边界:门禁验"脚本按其声明输出",不验"脚本计算正确"——伪造脚本打印正确哈希+期望数值即可过 rc0。完整性来自冻结输入字节与声明自洽,非数学。
- text-quote 锚带字节快照:
quote + locator + snapshot + snapshot_sha256;gate 核快照哈希 + 引用句须真实存在于快照文本(排版/空白归一化比对)。机器核的是"引用句在这份快照里";快照是否确为现实源头仍须人工/AI 核。 - PASS 带影子:空 doubt 表面 = peak 峰值信号,无影子的 PASS 最该被盯。
- 零依赖承诺:gate 只用 Python stdlib;引入依赖即破坏核心卖点。
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.
- 9d ago First seen · 42 lines · 1,173 tokens per session scan A 56736ebb0a5a
verifiable-claim-seed CLAUDE.md is an instructions file published in the GitHub repository elwsls/verifiable-claim-seed (0 stars, last pushed 17d ago), licensed MIT. It adds 1,173 tokens to every session, about $0.0059 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.