{"slug": "three-documents-that-keep-my-ai-coding-agent-honest-free-templates-claude-code", "title": "Three documents that keep my AI coding agent honest (free templates + Claude Code skill)", "summary": "A solo developer running a one-person industrial sensing R&D operation released ai-rd-process-kit, an MIT-licensed set of Markdown templates and a Claude Code skill that forces AI coding agents to write plan, design and requirements-to-test documents before implementing. The kit also includes a lessons-learned file the agent updates itself after failures, and a 13-rule CLAUDE.md example; the developer reports the approach fixed recurring agent failures that better models did not.", "body_md": "I run a one-person R&D operation that ships industrial sensing products — analogue boards, microcontroller firmware, PC tools. Most of the typing is done by AI coding agents (mainly Claude Code). They are fast, and for a year they failed in the same four ways:\n\nNone of this was fixed by a better model. It was fixed by a process the agent cannot skip. I've generalized it into a small kit and put it on GitHub under MIT: **[ai-rd-process-kit](https://github.com/onepersonrd/ai-rd-process-kit)**.\n\nBefore any implementation, the agent writes three documents, and I accept them:\n\nThen the agent works in small checked pieces, updates the documents in the same change that alters the design, and when it fails, **it writes the lesson itself**: situation, cause, prevention. It reads that file at the start of every session.\n\n| % | Means | \n|---|---|\n| 0 | Not started | \n| 25 | Started | \n| 50 | Draft complete, not self-checked | \n| 75 | Waiting for review, or under test | \n| 100 | Accepted in review and tests passed | \n\nUnverified work stays at 75. Where things can be counted, they are counted: `tests passed 38/52 → 73%`.\n\n**\"Not found\" is not \"does not exist.\"** The agent searched a rulebook for two keywords, found nothing, and reported that no rule applied. The rule existed under different wording. Prevention: questions of the form \"is there a rule about X\" are answered by reading the relevant chapters, and the report says what was searched and what was not read.\n\n**ERC passed, the netlist had three shorts.** An auto-generated schematic passed the electrical rules check. The netlist showed a rotated protection diode shorting two supply rails, a pull-up routed onto a data line, and a duplicated reference designator. Prevention: after generating a schematic, export the netlist and script-check supply/ground separation, polarity of oriented parts and duplicate designators before layout.\n\n`templates/` — plan, design doc, requirements↔test matrix, lessons-learned (with four real, anonymized examples)`rules/CLAUDE.md.example` — 13 promises for the root of your project`skills/rd-process/SKILL.md` — a Claude Code skill: session start, create the docs, work, test, log, session end\nFive-minute setup: copy the templates into `docs/`, put the rules in `CLAUDE.md`, install the skill, and say \"plan this\". If the agent starts coding before showing you the scope table, the rules aren't loaded.\n\nNot a methodology, not a tool, not a prompt pack. Four Markdown files and a habit. It works with any agent that reads an instruction file; the skill is for Claude Code.\n\nIf you try it, I'd like to know which rule your agent broke first. Mine was #4.\n\n*Disclosure: this post and the templates were drafted with an AI assistant and rewritten by me from first-hand use.*", "url": "https://wpnews.pro/news/three-documents-that-keep-my-ai-coding-agent-honest-free-templates-claude-code", "canonical_source": "https://dev.to/onepersonrd/three-documents-that-keep-my-ai-coding-agent-honest-free-templates-claude-code-skill-63f", "published_at": "2026-10-28 06:06:29+00:00", "updated_at": "2026-10-28 06:11:18.915148+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "ai-products"], "entities": ["Claude Code", "ai-rd-process-kit", "GitHub", "Anthropic"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/three-documents-that-keep-my-ai-coding-agent-honest-free-templates-claude-code", "markdown": "https://wpnews.pro/news/three-documents-that-keep-my-ai-coding-agent-honest-free-templates-claude-code.md", "text": "https://wpnews.pro/news/three-documents-that-keep-my-ai-coding-agent-honest-free-templates-claude-code.txt", "jsonld": "https://wpnews.pro/news/three-documents-that-keep-my-ai-coding-agent-honest-free-templates-claude-code.jsonld"}}