参考文献#
本页列出本书引用到的每一件作品。第一小节展示正文中实际被引用到的那些作品；第二小节展示维护在 _bib/*.bib 中的完整精选阅读单（包括尚未被引用、但留给附录 C 使用的作品）。
本书实际引用的作品#
Gojko Adzic. Specification by Example: How Successful Teams Deliver the Right Software. Manning Publications, 2011. ISBN 9781617290084.
Alberto Bacchelli and Christian Bird. Expectations, outcomes, and challenges of modern code review. In Proceedings of the 35th International Conference on Software Engineering (ICSE). 2013. doi:10.1109/ICSE.2013.6606617.
Kent Beck. Test-Driven Development: By Example. Addison-Wesley Professional, 2002. ISBN 9780321146533.
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and others. Language models are few-shot learners. 2020. GPT-3; foundational evidence for in-context learning. URL: https://arxiv.org/abs/2005.14165, arXiv:2005.14165.
Melvin E. Conway. How do committees invent? Datamation, 14(4):28–31, 1968.
Ward Cunningham. The WyCash portfolio management system. In Addendum to the Proceedings of the 1992 OOPSLA. 1992. The original “technical debt” metaphor. doi:10.1145/157709.157715.
Walter Fan. Ai coding 的三大护法：可验证、可观察、可理解. Walter Fan's Journal, 2026. Original source for the “Three Guardians” (SDD/TDD/MDD) thesis; forms the backbone of Chapter 04. URL: https://walterfan.com/journal/ai_coding_3_protector.
Walter Fan. Lazy AI Coder: an AI-augmented coding workbench. GitHub repository, 2026. The host repository of this book; Chapter 11's four-act case study draws commits from this project. URL: walterfan/async-harness-book.
Walter Fan. lazy-scrum-team: a multi-role scrum skill for AI coding agents. ExampleCorp Dev Skills repository, 2026. Source of the Artefact State Model, Rework Matrix, and Verification table patterns adopted in Ch. 09 and expanded in Ch. 12. URL: example-org/examplecorp-dev-skills.
Michael C. Feathers. Working Effectively with Legacy Code. Prentice Hall, 2004. ISBN 9780131177055.
Neal Ford, Rebecca Parsons, and Patrick Kua. Building Evolutionary Architectures: Support Constant Change. O'Reilly Media, 2017. ISBN 9781491986363.
Nicole Forsgren, Jez Humble, and Gene Kim. Accelerate: The Science of Lean Software and DevOps. IT Revolution Press, 2018. ISBN 9781942788331.
Martin Fowler. Harness engineering: shaping the environment in which coding agents work. martinfowler.com, 2026. Placeholder citation pending publication; Fowler's essay is the most-cited introduction to the term. Replace URL on archive. URL: https://martinfowler.com/articles/harness-engineering.html.
Georgios Gousios, Martin Pinzger, and Arie van Deursen. An exploratory study of the pull-based software development model. Proceedings of the 36th International Conference on Software Engineering (ICSE), 2014. doi:10.1145/2568225.2568260.
Jez Humble and David Farley. Continuous Delivery: Reliable Software Releases through Build, Test, and Deployment Automation. Addison-Wesley Professional, 2010. ISBN 9780321601919.
Chip Huyen. AI Engineering: Building Applications with Foundation Models. O'Reilly Media, 2025. ISBN 9781098166304. Systems-level view of building with LLMs; Chapter 3 "Evaluation" motivates the TDD guardian in 4.
Ralf Jung, Jacques-Henri Jourdan, Robbert Krebbers, and Derek Dreyer. RustBelt: securing the foundations of the Rust programming language. In Proc. 45th ACM SIGPLAN Symposium on Principles of Programming Languages (POPL). 2018. Foundational result motivating Rust's ownership discipline as a harness-like constraint; cited in Ch. 09 Tauri-Todo arc. doi:10.1145/3158154.
Andrej Karpathy. Context is the new code. Twitter/X thread, later syndicated as blog post, 2025. Popularized “context engineering” framing referenced in Ch. 02's four-stage evolution. URL: https://karpathy.bearblog.dev/context-is-the-new-code/.
Meir M. Lehman. Programs, life cycles, and laws of software evolution. Proceedings of the IEEE, 68(9):1060–1076, 1980. doi:10.1109/PROC.1980.11805.
Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020). 2020. URL: https://arxiv.org/abs/2005.11401.
Charity Majors, Liz Fong-Jones, and George Miranda. Observability Engineering: Achieving Production Excellence. O'Reilly Media, 2022. ISBN 9781492076445.
Cyrille Martraire. Living Documentation: Continuous Knowledge Sharing by Design. Addison-Wesley Professional, 2019. ISBN 9780134689326.
Bertrand Meyer. Applying “design by contract”. Computer, 25(10):40–51, 1992. doi:10.1109/2.161279.
Ashley Mills. The socratic method in software design. Essay, self-published, 2015. Placeholder for the Socratic-method design essay cited in Ch. 11; replace with canonical source on archival sweep. URL: https://example.org/socratic-software-design.
Sida Peng, Eirini Kalliamvakou, Peter Cihon, and Mert Demirer. The impact of AI on developer productivity: evidence from GitHub Copilot. 2023. URL: https://arxiv.org/abs/2302.06590, arXiv:2302.06590.
Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. Toolformer: language models can teach themselves to use tools. 2023. URL: https://arxiv.org/abs/2302.04761, arXiv:2302.04761.
Ken Schwaber and Jeff Sutherland. The 2020 Scrum Guide. Scrum.org, 2020. URL: https://scrumguides.org/scrum-guide.html.
D. Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-François Crespo, and Dan Dennison. Hidden technical debt in machine learning systems. In Advances in Neural Information Processing Systems 28 (NeurIPS 2015). 2015. URL: https://papers.nips.cc/paper_files/paper/2015/hash/86df7dcfd896fcaf2674f757a2463eba-Abstract.html.
Edith Tom, Aybuke Aurum, and Richard Vidgen. An exploration of technical debt. 2013. Classification of technical-debt types; used in Ch. 15 to score Lazy AI Coder's backlog. doi:10.1016/j.jss.2012.12.052.
Joseph Vincent. Superpowers: a prompt scaffolding library for claude code. GitHub & personal blog, 2025. Walkthrough essay accompanying the Superpowers release used as the Ch. 11 case study. URL: obra/superpowers.
Joseph Vincent. Obra/superpowers. GitHub repository, 2025. Repository artefact for Chapter 08; mirrored under \texttt oss/superpowers/. URL: obra/superpowers.
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models. 2022. URL: https://arxiv.org/abs/2201.11903, arXiv:2201.11903.
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. ReAct: synergizing reasoning and acting in language models. 2022. Reason + Act loop; canonical citation for agent scaffolds. URL: https://arxiv.org/abs/2210.03629, arXiv:2210.03629.
Andreas Zeller. Why programs fail: a guide to systematic debugging. 2009. Cited in Ch. 11 for the systematic-debugging lineage behind the Superpowers debugging skill.
Handong Zhang. Harness engineering: from claude code to ai coding (《马书》). Self-published, 2026. Reverse-engineering of Claude Code's harness; used as the Ch. 13 case study. This book's Ch. 13 builds on the《马书》with a disclaimer about the unofficial nature of the findings. URL: ZhangHanDong/harness-engineering-from-cc-to-ai-coding.
Albert Ziegler, Eirini Kalliamvakou, X. Alice Li, Andrew Rice, Devon Rifkin, Shawn Simister, Ganesh Sittampalam, and Edward Aftandilian. Productivity assessment of neural code completion. 2022. Companion quantitative study for Copilot's harness claims. URL: https://arxiv.org/abs/2205.06537, arXiv:2205.06537.
Agentic AI Foundation. agents.md: open format for coding agent instructions. Open standard website, 2025. Vendor-neutral entry-file standard cited in Ch. 03 and Ch. 08 as the canonical SDD x Bridle file. URL: https://agents.md.
Anthropic. Building effective agents. Anthropic Engineering Blog, 2024. Canonical vendor articulation of the agent-engineering boundary cited in Ch. 03's comparison table. URL: https://www.anthropic.com/engineering/building-effective-agents.
Anthropic. Claude Code skills: structured prompt scaffolds. Anthropic documentation, 2024. Official documentation of the Skill format cited in Ch. 11. URL: https://docs.anthropic.com/en/docs/claude-code/skills.
Anthropic. Claude Code: an agentic coding harness. Anthropic Documentation, 2024. Primary source for Chapter 10's analysis; the proprietary harness whose design is reverse-engineered in《马书》. URL: https://docs.anthropic.com/claude/claude-code.
Anthropic. Model Context Protocol specification. Protocol specification and reference implementations, 2024. MCP schema referenced by the \texttt mcp-schema-check task in Ch. 15 and 14. URL: https://modelcontextprotocol.io.
Anthropic. Effective harnesses for long-running agents. Anthropic Engineering Blog, 2026. Vendor-side report on long-task agent harness engineering; cited in Ch. 03C's Provenance. URL: https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents.
CAR Research Collective. Control-agency-runtime: a decomposition for ai coding agents and the harnesscard reporting format. Working paper, 2025. Position paper introducing the CAR decomposition and HarnessCard template referenced in Chapters 05 and 13. Placeholder citation; replace DOI when published.
CNCF Platforms Working Group. CNCF platform engineering maturity model v1.1. Cloud Native Computing Foundation White Paper, 2024. Boundary reference for Platform Engineering in Ch. 03's comparison table. URL: https://tag-app-delivery.cncf.io/whitepapers/platform-eng-maturity-model/.
HKU Data Science Lab. OpenHarness: an open-source harness for LLM coding agents. GitHub repository, 2025. Primary case study for Chapter 07. Mirrored in this repo under \texttt oss/OpenHarness/. URL: HKUDS/OpenHarness.
LangChain. The anatomy of an agent harness. LangChain Engineering Blog, 2026. Source of the “Agent = Model + Harness” formula cited in Ch. 03C. URL: https://blog.langchain.com/the-anatomy-of-an-agent-harness/.
LangChain. Terminal-Bench 2.0: evaluating coding agents in full development environments. LangChain Engineering Blog, 2026. Canonical reference for the benchmark cited in Ch. 03 and Ch. 08. URL: https://blog.langchain.dev/terminal-bench-2/.
OpenAI Codex Team. Codex best practices: AGENTS.md, rules, hooks, memories, skills and worktrees. OpenAI Engineering Talks / public release notes, 2026. Vendor articulation of the Codex CLI's harness surfaces; primary source for Ch. 14's case study. URL: https://openai.com/codex.
OpenAI. Agentic coding: harness design for ChatGPT agents. OpenAI Engineering Blog, 2026. Vendor-side articulation of harness-as-product; cited for triangulation in Ch. 08 Provenance. URL: https://openai.com/index/agentic-coding-harness/.
Tauri Working Group. Tauri 2.0 security white paper. Tauri Project documentation, 2024. Primary security model for Tauri 2 cited in Ch. 09 Tauri-Todo hands-on arc. URL: https://tauri.app/v2/security/.
Thoughtworks Technology Radar. Architectural fitness function. Technology Radar, Techniques, 2026. Origin of the “architectural fitness function” vocabulary used in Ch. 03C.5 and Ch. 08. URL: https://www.thoughtworks.com/radar/techniques/architectural-fitness-function.
Thoughtworks Technology Radar. Harnesses for AI coding agents. Technology Radar Vol. 32, “Trial” ring, 2026. Industry validation of the harness-engineering idea; referenced in Ch. 03 and Ch. 08 Provenance. URL: https://www.thoughtworks.com/radar.
walkinglabs. Awesome Harness Engineering. GitHub curated list, 2026. Community-maintained reading list; cross-linked from Appendix C. URL: walkinglabs/awesome-harness-engineering.
完整精选阅读单#
本小节使用 :all: 强制渲染每一条条目，这样附录 C 就可以指向一份完整的阅读单 —— 哪怕此时还并非每一条都已被引用。按 sphinxcontrib-bibtex 的惯例，仅在本小节出现（而未在上面那个小节出现）的条目，是 不可 经由 {cite} 解析的 —— 它们按设计以"孤儿"书目条目的身份出现。
Gojko Adzic. Specification by Example: How Successful Teams Deliver the Right Software. Manning Publications, 2011. ISBN 9781617290084.
Alberto Bacchelli and Christian Bird. Expectations, outcomes, and challenges of modern code review. In Proceedings of the 35th International Conference on Software Engineering (ICSE). 2013. doi:10.1109/ICSE.2013.6606617.
Kent Beck. Test-Driven Development: By Example. Addison-Wesley Professional, 2002. ISBN 9780321146533.
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and others. Language models are few-shot learners. 2020. GPT-3; foundational evidence for in-context learning. URL: https://arxiv.org/abs/2005.14165, arXiv:2005.14165.
Melvin E. Conway. How do committees invent? Datamation, 14(4):28–31, 1968.
Ward Cunningham. The WyCash portfolio management system. In Addendum to the Proceedings of the 1992 OOPSLA. 1992. The original “technical debt” metaphor. doi:10.1145/157709.157715.
Walter Fan. Ai coding 的三大护法：可验证、可观察、可理解. Walter Fan's Journal, 2026. Original source for the “Three Guardians” (SDD/TDD/MDD) thesis; forms the backbone of Chapter 04. URL: https://walterfan.com/journal/ai_coding_3_protector.
Walter Fan. Lazy AI Coder: an AI-augmented coding workbench. GitHub repository, 2026. The host repository of this book; Chapter 11's four-act case study draws commits from this project. URL: walterfan/async-harness-book.
Walter Fan. lazy-scrum-team: a multi-role scrum skill for AI coding agents. ExampleCorp Dev Skills repository, 2026. Source of the Artefact State Model, Rework Matrix, and Verification table patterns adopted in Ch. 09 and expanded in Ch. 12. URL: example-org/examplecorp-dev-skills.
Michael C. Feathers. Working Effectively with Legacy Code. Prentice Hall, 2004. ISBN 9780131177055.
Neal Ford, Rebecca Parsons, and Patrick Kua. Building Evolutionary Architectures: Support Constant Change. O'Reilly Media, 2017. ISBN 9781491986363.
Nicole Forsgren, Jez Humble, and Gene Kim. Accelerate: The Science of Lean Software and DevOps. IT Revolution Press, 2018. ISBN 9781942788331.
Martin Fowler. Harness engineering: shaping the environment in which coding agents work. martinfowler.com, 2026. Placeholder citation pending publication; Fowler's essay is the most-cited introduction to the term. Replace URL on archive. URL: https://martinfowler.com/articles/harness-engineering.html.
Georgios Gousios, Martin Pinzger, and Arie van Deursen. An exploratory study of the pull-based software development model. Proceedings of the 36th International Conference on Software Engineering (ICSE), 2014. doi:10.1145/2568225.2568260.
Jez Humble and David Farley. Continuous Delivery: Reliable Software Releases through Build, Test, and Deployment Automation. Addison-Wesley Professional, 2010. ISBN 9780321601919.
Chip Huyen. AI Engineering: Building Applications with Foundation Models. O'Reilly Media, 2025. ISBN 9781098166304. Systems-level view of building with LLMs; Chapter 3 "Evaluation" motivates the TDD guardian in 4.
Ralf Jung, Jacques-Henri Jourdan, Robbert Krebbers, and Derek Dreyer. RustBelt: securing the foundations of the Rust programming language. In Proc. 45th ACM SIGPLAN Symposium on Principles of Programming Languages (POPL). 2018. Foundational result motivating Rust's ownership discipline as a harness-like constraint; cited in Ch. 09 Tauri-Todo arc. doi:10.1145/3158154.
Stephan Jung. Fast feedback loops as a design constraint. Engineering Productivity Blog, 2018. Placeholder; will be replaced with canonical source on the feedback-loop latency argument cited in Ch. 09. URL: https://example.org/feedback-loops-as-constraint.
Andrej Karpathy. Context is the new code. Twitter/X thread, later syndicated as blog post, 2025. Popularized “context engineering” framing referenced in Ch. 02's four-stage evolution. URL: https://karpathy.bearblog.dev/context-is-the-new-code/.
Meir M. Lehman. Programs, life cycles, and laws of software evolution. Proceedings of the IEEE, 68(9):1060–1076, 1980. doi:10.1109/PROC.1980.11805.
Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020). 2020. URL: https://arxiv.org/abs/2005.11401.
Charity Majors, Liz Fong-Jones, and George Miranda. Observability Engineering: Achieving Production Excellence. O'Reilly Media, 2022. ISBN 9781492076445.
Cyrille Martraire. Living Documentation: Continuous Knowledge Sharing by Design. Addison-Wesley Professional, 2019. ISBN 9780134689326.
Bertrand Meyer. Applying “design by contract”. Computer, 25(10):40–51, 1992. doi:10.1109/2.161279.
Ashley Mills. The socratic method in software design. Essay, self-published, 2015. Placeholder for the Socratic-method design essay cited in Ch. 11; replace with canonical source on archival sweep. URL: https://example.org/socratic-software-design.
Sida Peng, Eirini Kalliamvakou, Peter Cihon, and Mert Demirer. The impact of AI on developer productivity: evidence from GitHub Copilot. 2023. URL: https://arxiv.org/abs/2302.06590, arXiv:2302.06590.
Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. Toolformer: language models can teach themselves to use tools. 2023. URL: https://arxiv.org/abs/2302.04761, arXiv:2302.04761.
Ken Schwaber and Jeff Sutherland. The 2020 Scrum Guide. Scrum.org, 2020. URL: https://scrumguides.org/scrum-guide.html.
D. Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-François Crespo, and Dan Dennison. Hidden technical debt in machine learning systems. In Advances in Neural Information Processing Systems 28 (NeurIPS 2015). 2015. URL: https://papers.nips.cc/paper_files/paper/2015/hash/86df7dcfd896fcaf2674f757a2463eba-Abstract.html.
Edith Tom, Aybuke Aurum, and Richard Vidgen. An exploration of technical debt. 2013. Classification of technical-debt types; used in Ch. 15 to score Lazy AI Coder's backlog. doi:10.1016/j.jss.2012.12.052.
Joseph Vincent. Superpowers: a prompt scaffolding library for claude code. GitHub & personal blog, 2025. Walkthrough essay accompanying the Superpowers release used as the Ch. 11 case study. URL: obra/superpowers.
Joseph Vincent. Obra/superpowers. GitHub repository, 2025. Repository artefact for Chapter 08; mirrored under \texttt oss/superpowers/. URL: obra/superpowers.
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models. 2022. URL: https://arxiv.org/abs/2201.11903, arXiv:2201.11903.
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. ReAct: synergizing reasoning and acting in language models. 2022. Reason + Act loop; canonical citation for agent scaffolds. URL: https://arxiv.org/abs/2210.03629, arXiv:2210.03629.
Andreas Zeller. Why programs fail: a guide to systematic debugging. 2009. Cited in Ch. 11 for the systematic-debugging lineage behind the Superpowers debugging skill.
Handong Zhang. Harness engineering: from claude code to ai coding (《马书》). Self-published, 2026. Reverse-engineering of Claude Code's harness; used as the Ch. 13 case study. This book's Ch. 13 builds on the《马书》with a disclaimer about the unofficial nature of the findings. URL: ZhangHanDong/harness-engineering-from-cc-to-ai-coding.
Albert Ziegler, Eirini Kalliamvakou, X. Alice Li, Andrew Rice, Devon Rifkin, Shawn Simister, Ganesh Sittampalam, and Edward Aftandilian. Productivity assessment of neural code completion. 2022. Companion quantitative study for Copilot's harness claims. URL: https://arxiv.org/abs/2205.06537, arXiv:2205.06537.
Agentic AI Foundation. agents.md: open format for coding agent instructions. Open standard website, 2025. Vendor-neutral entry-file standard cited in Ch. 03 and Ch. 08 as the canonical SDD x Bridle file. URL: https://agents.md.
Anthropic. Building effective agents. Anthropic Engineering Blog, 2024. Canonical vendor articulation of the agent-engineering boundary cited in Ch. 03's comparison table. URL: https://www.anthropic.com/engineering/building-effective-agents.
Anthropic. Claude Code skills: structured prompt scaffolds. Anthropic documentation, 2024. Official documentation of the Skill format cited in Ch. 11. URL: https://docs.anthropic.com/en/docs/claude-code/skills.
Anthropic. Claude Code: an agentic coding harness. Anthropic Documentation, 2024. Primary source for Chapter 10's analysis; the proprietary harness whose design is reverse-engineered in《马书》. URL: https://docs.anthropic.com/claude/claude-code.
Anthropic. Model Context Protocol specification. Protocol specification and reference implementations, 2024. MCP schema referenced by the \texttt mcp-schema-check task in Ch. 15 and 14. URL: https://modelcontextprotocol.io.
Anthropic. Effective harnesses for long-running agents. Anthropic Engineering Blog, 2026. Vendor-side report on long-task agent harness engineering; cited in Ch. 03C's Provenance. URL: https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents.
CAR Research Collective. Control-agency-runtime: a decomposition for ai coding agents and the harnesscard reporting format. Working paper, 2025. Position paper introducing the CAR decomposition and HarnessCard template referenced in Chapters 05 and 13. Placeholder citation; replace DOI when published.
CNCF Platforms Working Group. CNCF platform engineering maturity model v1.1. Cloud Native Computing Foundation White Paper, 2024. Boundary reference for Platform Engineering in Ch. 03's comparison table. URL: https://tag-app-delivery.cncf.io/whitepapers/platform-eng-maturity-model/.
HKU Data Science Lab. OpenHarness: an open-source harness for LLM coding agents. GitHub repository, 2025. Primary case study for Chapter 07. Mirrored in this repo under \texttt oss/OpenHarness/. URL: HKUDS/OpenHarness.
LangChain. The anatomy of an agent harness. LangChain Engineering Blog, 2026. Source of the “Agent = Model + Harness” formula cited in Ch. 03C. URL: https://blog.langchain.com/the-anatomy-of-an-agent-harness/.
LangChain. Terminal-Bench 2.0: evaluating coding agents in full development environments. LangChain Engineering Blog, 2026. Canonical reference for the benchmark cited in Ch. 03 and Ch. 08. URL: https://blog.langchain.dev/terminal-bench-2/.
OpenAI Codex Team. Codex best practices: AGENTS.md, rules, hooks, memories, skills and worktrees. OpenAI Engineering Talks / public release notes, 2026. Vendor articulation of the Codex CLI's harness surfaces; primary source for Ch. 14's case study. URL: https://openai.com/codex.
OpenAI. Agentic coding: harness design for ChatGPT agents. OpenAI Engineering Blog, 2026. Vendor-side articulation of harness-as-product; cited for triangulation in Ch. 08 Provenance. URL: https://openai.com/index/agentic-coding-harness/.
Tauri Working Group. Tauri 2.0 security white paper. Tauri Project documentation, 2024. Primary security model for Tauri 2 cited in Ch. 09 Tauri-Todo hands-on arc. URL: https://tauri.app/v2/security/.
Thoughtworks Technology Radar. Architectural fitness function. Technology Radar, Techniques, 2026. Origin of the “architectural fitness function” vocabulary used in Ch. 03C.5 and Ch. 08. URL: https://www.thoughtworks.com/radar/techniques/architectural-fitness-function.
Thoughtworks Technology Radar. Harnesses for AI coding agents. Technology Radar Vol. 32, “Trial” ring, 2026. Industry validation of the harness-engineering idea; referenced in Ch. 03 and Ch. 08 Provenance. URL: https://www.thoughtworks.com/radar.
walkinglabs. Awesome Harness Engineering. GitHub curated list, 2026. Community-maintained reading list; cross-linked from Appendix C. URL: walkinglabs/awesome-harness-engineering.