chaincompiler

WHAT: assemble a framework CHAPTER from the two rendered blog posts — run framework.assemble_chapter to copy Blog 1 + Blog 2 verbatim into a self-contained chapter dir, wire the relative cross-links + plugin/skill links + CTAs, and write the chapter.md manifest. WHEN: when Blog 1 + Blog 2 exist and need combining into the publishable chapter unit, or when the user says assemble a chapter / skill2framework (any of).

WHAT: produce Blog 2 of a framework CHAPTER — the mechanical deep-dive ('how it actually works') — for an already-built AIOS/package by reading its impl docs (README architecture sections, design docs, the code's module docstrings) and assembling a faithful mechanics-only article that links back to Blog 1. WHEN: when producing the deep-dive half of a chapter, when you need the technical how-it-works post Blog 1 links to, or when the user says blog 2 / deep dive / skill2framework (any of).

WHAT: the TERMINAL stage — fold a finished framework into the author's SkillTome (the top-level holder + search of all their frameworks) by running framework.fold_into_tome, which registers the framework as a row on a tome volume node's generated ## Frameworks table via skilltree's bind op. WHEN: when a framework package is finished and must be registered in the author's tome/volume, or when the user says fold into the tome / nomicon / skill2framework fold (any of).

WHAT: generate the FRAMEWORK SKILL for an already-built AIOS — the {aios}-volume (its SkillVolume face): one skill that indexes the AIOS's skills + rules + how they relate (as a diagram), gives a decision tree for what to do when, and ROUTES the agent into the AIOS dir. WHEN: when producing the index/router face of a framework package, or when the user says framework skill / volume / skill2framework (any of).

WHAT: produce Blog 1 of a framework CHAPTER — the narrative chapter-opener — for an already-built AIOS/package by reconstructing its journey from its own dir (CLAUDE.md, README, dev log) and FILLING framework.JourneyCore, then rendering with render_blog1 (never hand-write the blog). WHEN: when making a framework/chapter from something already built, when you need the story post that opens a chapter, or when the user says blog organ / narrative blog / skill2framework (any of).

WHAT: package a framework as a Claude Code PLUGIN (its operational face) — run framework.package_plugin to assemble plugin.json + skills/{aios}-volume/SKILL.md + the chapter bundled under resources/, with the skill's chapter links repathed to the bundle. WHEN: when a framework skill + chapter exist and need the installable plugin, or when the user says package the framework / plugin / skill2framework (any of).

Turn an already-built AIOS/package into a framework chapter — narrative blog + deep-dive blog → chapter → {aios}-volume index skill → plugin → folded into the author's SkillTome.

Use to refuse AI slop on every output: fix the sense, define the valid type, name the failure mode (emit-P-without-P-ness), define P-ness (the gate) and refuse the failure, grade every correspondence (G0–G9, never round up), commit, then actualize. The anti-slop define-validity-then-emit persona.

Roll the per-chain-type generators (AC/CoR/SC) into ONE callable that renders a chain sequence.

Construct a whole cognition-language for a domain (AC + CoR + SC) in one call (the AIOS top-door).

ACCC — forge an attention-chain language, gate candidates against it, package it as a SKILL.md.

CORCC — forge a chain-of-reasoning persona (NESTS an attention chain); lint + package it.

SCCC — forge a skill-chain language: resolve [ac|cor|skill] steps to packages and roll them up.

Generate a full persona prompt from a small spec (block types + a chain-of-reasoning DSL block).

Compose a prompt as a MetaStack of RenderablePiece blocks (deterministic data → prompt).

A named persona from a ROLE-intro block + a chain sequence; XML by default, or markdown mode.

Use when steering retrieval with hidden in-band glyph markers — an LLM annotates a corpus with a controlled emoji/glyph vocabulary that biases search (lexical facet + dense direction) but is stripped from returned text; also for grading a RAG corpus and searching with grade badges, and for authoring/persisting a glyph "legend". Triggers on "glyphsteer", "emoji annotation", "hidden retrieval markers", "steer RAG", "grade a corpus", "facet by sentiment/grade", "glyph legend", "annotate corpus for search".

Compile an archetype as a STATE MACHINE (not a noun) — Persona/Shadow/Self/Odyssey/Becoming — generating the missing aspects from one seed, building the multi-journey Odyssey, validating C1–C6, and emitting Cypher/Prolog/JSON or a loadable SKILL.md. Use when asked to model archetypes, individuation, Jungian stacks, a pantheon, the hero's journey/odyssey, Becoming/type-lift, or "compile the transformation law not the list" for characters/roles/myth.

Orientation when working IN the chaincompiler repo — what the system is, where things live, and the discipline. Use when developing/extending ChainCompiler, ACCC/CORCC/SCCC, skilltree, the SI, the marketplace, or the Skill OS.

How to verify agent/COG/gate/AIOS behavior WITHOUT calling LLMs or writing tautology asserts — by triggering the real thing in the real substrate and observing the state-change. Use when you're about to "test" something cognitive/agentic, when a test feels like `assert True == True`, or when you need to prove a gate/effect actually works. Read the story; copy the moves.

The primary technology — impose a navigable TREE on the flat `.claude/skills` substrate, and keep it COHERENT. Use when you see a `[SKILLTREE]` system-notification warning (the tree decohered — recohere it), when a `.claude/skills` is a flat forest you can't navigate, when you need to view/engineer/assign-coords on a skill tree, or when you must navigate a big tree without loading the pile. Triggers: "tree decoherence", "recohere", "skilltree", "treeify skills", "the tree shape", "flat forest", "bare forest", "cat down the tree".

How the bandit (the default ChainSelector persona) rolls up the AC→CoR→SC algebra and CLOSES it into a domain-specific persona — a self-contained "bandit chain system" that builds its own KB and improves itself via GlyphSteer chains. Use when asked to mint a domain agent, "roll up an algebra", close a chain system, make a self-improving persona, or hierarchicalize the bandit over its own parts.

Use when running GlyphSteer's DENSE regime — embedding-based emoji steering via the containerized ONNX sidecar. Covers standing up the glyphsteer-serve Docker image, the MANDATORY emoji-collapse gate (many models map all emoji to one token), the magnitude probe, and the anchor metric-reshape (steer.sim_eff). Triggers on "glyphsteer dense", "embedding steering", "emoji direction", "glyphsteer sidecar", "magnitude probe", "anchor reshape", "is the dense nudge big enough".

Use when steering retrieval with hidden in-band markers — annotating a RAG corpus with a controlled emoji/glyph vocabulary that biases search (lexical facet + dense direction) but is stripped from returned text. Triggers on "glyph steer", "emoji annotation", "hidden retrieval markers", "steer RAG", "facet by sentiment", "annotate corpus for search".

Run ChainCompiler chain-dialect programs and turn skill trees into MCPs. Use to forge languages, build/walk skill trees, or execute a cognition chain.