Borrowing it
Nothing to install: this file belongs to DavidLam-oss/obsidian-wechat-converter. 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/DavidLam-oss/obsidian-wechat-converter/main/.claude/skills/openprd-discovery-loop/SKILL.mdgit clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converterWrote 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/davidlam-oss/obsidian-wechat-converter/openprd-discovery-loop)<a href="https://agentmods.dev/skills/davidlam-oss/obsidian-wechat-converter/openprd-discovery-loop"><img src="https://agentmods.dev/badge/skills/davidlam-oss/obsidian-wechat-converter/openprd-discovery-loop/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/skills/davidlam-oss/obsidian-wechat-converter/openprd-discovery-loop"><img src="https://agentmods.dev/badge/skills/davidlam-oss/obsidian-wechat-converter/openprd-discovery-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.00878 |
| Opus 5 | $0.00013 | $0.00439 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
openprd-discovery-loop 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 5d 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.
What it actually says
OpenPrd Discovery Loop
当用户要求继续、深挖、补全、对比、复刻、全面梳理 requirements,或进行大量只读扫描时,使用这份 skill。
大量只读扫描调度
- 日常任务仍由主 agent 先直接读取本地上下文;不要因为用户只说“看看、分析、梳理、定位、排查”就自动并行。
- 用户明确要求深度分析、深入调研、全面梳理、多角度评估、交叉验证、并行排查、对标复刻或风险审查时,优先考虑只读 subagent。
- 任务需要同时阅读多个目录、文档、模块、日志、历史实现或参考项目,且并行收集证据能明显减少主上下文污染或节省时间时,可以启动。
- 任务涉及外部技术事实、公开仓库对标、复杂排障、发布风险或安全风险,且需要独立复核时,可以启动;仍必须遵守 Context7、DeepWiki、secrets-vault 和长文件门禁。
- 用户明确说“不用 subagent / 直接做 / 先别并行 / 只回答”时,不启动。
- 单文件小改、明确文案微调、简单命令、非常短的问题或清晰 bug 修复,默认不启动。
- 一旦进入深度研究型 subagent 流程,默认使用 3 个只读 subagent:2 个独立调研执行者 + 1 个审查/交叉验证者。
- 最多启动 5 个 subagent:最多 4 个调研执行者 + 1 个审查者。只有任务天然拆成 4 个互不冲突的研究分支时才扩到 5 个。
- 代码与文档调研优先使用
spark-code-researcher、spark-doc-reader或documentation-explore;对标复刻用electron-parity-mapper;安装发布或渠道排障用release-diagnostics-researcher、channel-debug-researcher;审查与风险扫描用skill-workflow-reviewer、security-risk-researcher。 - 每个 subagent 只回答一个清晰问题,不再继续 spawn;主 agent 负责决策、整合和所有写入,subagent 只做只读调研、归纳和交叉验证。
- subagent 输出必须回到主 agent 汇总;写入 discovery claim、requirements、specs 或 tasks 前,主 agent 必须把结论映射到证据路径、置信度和未解决问题。
循环
- 用
openprd discovery . --mode <brownfield|reference|requirement>启动或恢复。 - 每次只推进一个有证据支撑的覆盖项。
- 报告运行健康前,用
openprd discovery . --verify做校验。 - 通过
openprd standards . --verify保持基线文档标准同步。 - 单个任务完成后只保留 task-scoped evidence;阶段收口或整体实现完成后,再用
openprd quality . --verify审查 HTML 质量评估报告里的场景标签、必需 EVO 门禁、日志、业务护栏、冒烟覆盖、性能和知识缺口。
深度规则
- 每个 claim 都要带来源、证据路径和置信度。
- 推断出的行为不能直接变成 accepted requirement,必须保持可评审。
- 大型任务文件必须分片并通过校验。
- 只有在覆盖耗尽、被阻塞,或明确交接后才停止。
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.
- 5d ago First seen · 45 lines · 26 tokens per session scan A f1955509c75c
openprd-discovery-loop is a skill published in the GitHub repository DavidLam-oss/obsidian-wechat-converter (307 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 878 once invoked, about $0.0001 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 2026-09-04.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…