zero-hallucination-coder

v2.10.3

A disciplined coding pipeline that grounds code in verified structure before a line is written: Discuss -> Map -> Decompose -> Execute -> Verify, with a lazy-senior-dev YAGNI ladder that deletes unnecessary code first. No invented APIs, no assumed imports, no placeholder code. Opt-in for high-stakes, complex, or multi-file work; not for trivial edits. Synthesizes four MIT/open-source projects (Ralph, GSD Core, Graphify, Ponytail).

Claude Code1 skill

by Alireza RezvaniMIT24.2kupdated 10 hours ago

Source

$ git clone https://github.com/alirezarezvani/claude-skills

Clone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is engineering/zero-hallucination-coder/ inside the repository.

Layout

engineering/zero-hallucination-coder/

├── .claude-plugin/plugin.json
└── skills/zero-hallucination-coder/SKILL.md

Skills1

zero-hallucination-coderskills/zero-hallucination-coder/SKILL.md

Runs a disciplined Discuss -> Map -> Decompose -> Execute -> Verify loop that grounds code in verified structure — no invented APIs, no assumed imports, no placeholder code — with a lazy-senior-dev YAGNI ladder that deletes unnecessary code before it is written. Use when a coding task is high-stakes, complex, or spans existing code (auth, databases, migrations, multi-file features), or when the user explicitly asks to plan carefully before coding, avoid hallucinated code, or work rigorously. Not for trivial edits, typos, or throwaway one-off scripts — those do not need the full loop.

Manifests1

engineering/zero-hallucination-coder/.claude-plugin/plugin.json

{
  "name": "zero-hallucination-coder",
  "description": "A disciplined coding pipeline that grounds code in verified structure before a line is written: Discuss -> Map -> Decompose -> Execute -> Verify, with a lazy-senior-dev YAGNI ladder that deletes unnecessary code first. No invented APIs, no assumed imports, no placeholder code. Opt-in for high-stakes, complex, or multi-file work; not for trivial edits. Synthesizes four MIT/open-source projects (Ralph, GSD Core, Graphify, Ponytail).",
  "version": "2.10.3",
  "author": {
    "name": "Alireza Rezvani",
    "url": "https://alirezarezvani.com"
  },
  "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/engineering/zero-hallucination-coder",
  "repository": "https://github.com/alirezarezvani/claude-skills",
  "license": "MIT",
  "skills": [
    "./skills/zero-hallucination-coder"
  ],
  "attribution": {
    "contributed_by": "mehanshbarthwal-lab (https://github.com/mehanshbarthwal-lab), PR #854",
    "synthesizes": [
      "Ralph — @snarktank (https://github.com/snarktank/ralph): atomic PRD loop, fresh-context per story",
      "GSD Core — @open-gsd (https://github.com/open-gsd/gsd-core): phase loop, context-rot prevention, STATE.md memory",
      "Graphify — @safishamsi (https://github.com/safishamsi/graphify): KNOWN/INFERRED/UNKNOWN codebase mapping",
      "Ponytail — @DietrichGebert (https://github.com/DietrichGebert/ponytail): lazy-senior-dev six-rung hierarchy"
    ],
    "derivation_note": "Concept + SKILL.md contributed via PR #854. Hardened for this repo: scoped to opt-in activation, embedded multi-method install guide trimmed, plugin.json and layout aligned to the engineering standalone-plugin convention."
  }
}