feat(skill): introduce CONCEPTS.md as shared vocabulary substrate

AGENTS.md

@@ -50,6 +50,7 @@ plugins/          Plugin workspaces (compound-engineering, coding-tutor)
 .claude-plugin/   Claude marketplace catalog metadata
 tests/            Converter, writer, and CLI tests + fixtures
 docs/             Requirements, plans, solutions, and target specs
+CONCEPTS.md       Shared domain vocabulary (glossary of project-specific terms)
 ```
 
 ## Repo Surfaces

CONCEPTS.md

@@ -0,0 +1,64 @@
+# Concepts
+
+Shared domain vocabulary for this project — entities, named processes, and status concepts with project-specific meaning. Seeded with core domain vocabulary, then accretes as ce-compound and ce-compound-refresh process learnings; direct edits are fine. Glossary only, not a spec or catch-all.
+
+## The plugin and its parts
+
+### Plugin
+A distributable bundle of Skills, Agents, Commands, and Hooks (optionally MCP servers) described by a single manifest and installed into a coding-agent platform as one unit — the artifact the Converter translates for non-Claude Targets and the Marketplace distributes.
+
+### Skill
+A slash-invoked capability defined in its own directory, and the primary entry point a user reaches for. A Skill orchestrates: it can progressively pull in its own reference files as needed and dispatch Agents to do scoped work. Distinct from an Agent in that a Skill is user-invoked and coordinates, whereas an Agent is dispatched by a Skill.
+
+### Agent
+A specialized, single-purpose worker a Skill dispatches to run in its own isolated context and return a result, rather than to converse with the user. Also called a subagent. Agents are not invoked directly by users; a Skill decides when and how many to run.
+
+## Conversion
+
+### Target
+A destination coding-agent platform other than Claude Code (OpenCode, Codex, Gemini, and others) that a Plugin is converted into and installed onto, each with its own file layout and capability mapping. Also called a target provider.
+
+A Plugin is installed to a Target at one of two scopes: global (user-wide) or per-workspace.
+
+### Converter
+The step that transforms a parsed Plugin into one Target's in-memory form, mapping tools, permissions, hooks, and model names explicitly rather than by convention.
+
+### Writer
+The step that emits a Target's converted Bundle onto disk, in that Target's expected paths and merge semantics. Paired with a Converter, one per Target.
+
+### Bundle
+The in-memory converted form of a Plugin for a single Target — the handoff a Converter produces and a Writer consumes.
+
+### Marketplace
+The catalog metadata listing installable plugins and their versions for distribution, kept consistent with each Plugin's manifest by release validation.
+
+## Compound engineering
+
+### Compound engineering
+The methodology this project embodies: structure engineering work so each unit makes the next one easier, capturing reusable knowledge as you go so the toolset gets smarter with every use.
+
+### Pipeline
+The chained progression of Skills that carries a piece of work from strategy and ideation through brainstorm, plan, execution, and review, and closes by capturing what was learned. Each stage hands a durable artifact to the next, and research is gathered at the stage that needs it rather than re-gathered downstream.
+
+### Learning
+A documented solution to a past problem — a bug fix, a convention, or a workflow pattern — stored as the unit of compounded knowledge so future work can find and reuse it. Also called a solution doc. Carries structured metadata (category, tags, problem type) for retrieval; its creation date lives in the entry, not the filename.
+
+### Pattern doc
+Guidance generalized from several Learnings into a broader rule. Higher-leverage than any single incident-level Learning, and higher-risk when stale, because future work treats it as broadly applicable.
+
+## Review and workflow vocabulary
+
+### Reviewer persona
+A single-lens reviewer Agent that evaluates work from one specific perspective — security, correctness, scope, design, and so on. Review Skills dispatch a panel of personas and merge their findings.
+
+### Confidence anchor
+A discrete, self-scored confidence value on a fixed small scale, each level tied to a behavioral criterion the model can honestly apply, used to gate and rank review findings instead of a continuous score that invites false precision. Each review Skill sets its own actionable threshold; corroboration across personas promotes a finding by one level.
+
+### Autofix class
+The classification of a review finding by how safely its proposed fix can be applied: applied silently, applied only after user confirmation, left for a human to resolve, or recorded as advisory with no action.
+
+### Headless mode
+An explicit opt-in mode that runs a Skill unattended, with no user prompts — it produces a written report as its deliverable and conservatively defers genuinely ambiguous decisions rather than guessing.
+
+### Beta skill
+A parallel copy of a stable Skill, suffixed `-beta`, used to trial a new version alongside the stable one without disrupting users. Invoked manually (model auto-invocation is disabled); promoting it to stable is an orchestration change, not just a rename — every caller must move in the same change so none silently inherits stale defaults.

plugins/compound-engineering/AGENTS.md

@@ -12,7 +12,7 @@ They supplement the repo-root `AGENTS.md`.
 Consequences:
 
 - Behavioral rules that govern skill *runtime* behavior must live inside the skill itself — in `SKILL.md` or files under its `references/`. Guidance placed in this file is invisible at runtime.
-- When two or more skills share a behavioral principle, duplicate the guidance into each skill (inline for short rules, `references/` for longer ones). There is no cross-skill shared-file mechanism (see "File References in Skills" below).
+- When two or more skills share a behavioral principle, duplicate the guidance into each skill (inline for short rules, `references/` for longer ones). There is no cross-skill shared-file mechanism (see "File References in Skills" below). When a reference file is duplicated across skills (e.g., `concepts-vocabulary.md` in both `ce-compound/references/` and `ce-compound-refresh/references/`), edits must be applied to every copy in the same commit. Drift between copies produces inconsistent agent behavior depending on which skill loaded.
 - Do not propose that runtime guidance for ce-ideate, ce-brainstorm, ce-plan, or any other skill live in this AGENTS.md or in the repo-root AGENTS.md. Those files only shape how contributors edit the plugin.
 
 This is easy to miss because authoring feels like using: you edit the plugin while running inside this repo, and the repo's AGENTS.md is loaded — but that load does not follow the installed skill into a user's environment.

plugins/compound-engineering/agents/ce-learnings-researcher.md

@@ -18,6 +18,12 @@ Past learnings span multiple shapes:
 
 Treat all of these as candidates. Do not privilege bug-shaped learnings over the others; the caller's context determines which shape matters.
 
+## Step 0: Ground in CONCEPTS.md (if present)
+
+Before searching `docs/solutions/`, check whether `CONCEPTS.md` exists at the repo root. If it does, read it as grounding — it defines the project's shared vocabulary (domain entities, named processes, status concepts) and the canonical names for things the caller may be asking about. Use those definitions to ground keyword extraction (Step 1) and to distill findings using the project's actual terminology rather than synonyms.
+
+If `CONCEPTS.md` does not exist, skip this step entirely and proceed to Step 1.
+
 ## Search Strategy (Grep-First Filtering)
 
 The `docs/solutions/` directory contains documented learnings with YAML frontmatter. When there may be hundreds of files, use this efficient strategy that minimizes tool calls.

plugins/compound-engineering/skills/ce-brainstorm/SKILL.md

@@ -137,7 +137,7 @@ Scan the repo before substantive brainstorming. Match depth to scope:
 
 **Standard and Deep** — Two passes:
 
-*Constraint Check* — Check project instruction files (`AGENTS.md`, and `CLAUDE.md` only if retained as compatibility context) for workflow, product, or scope constraints that affect the brainstorm. Also read `STRATEGY.md` if it exists — the product's target problem, approach, persona, and active tracks are direct input to what this brainstorm should deliver and should shape scope, success criteria, and which approaches are aligned vs out-of-scope. If these add nothing, move on.
+*Constraint Check* — Check project instruction files (`AGENTS.md`, and `CLAUDE.md` only if retained as compatibility context) for workflow, product, or scope constraints that affect the brainstorm. Also read `STRATEGY.md` if it exists — the product's target problem, approach, persona, and active tracks are direct input to what this brainstorm should deliver and should shape scope, success criteria, and which approaches are aligned vs out-of-scope. Also read `CONCEPTS.md` at repo root if it exists — the project's authoritative vocabulary. Use these names in dialogue, approaches, and the requirements doc; map user-offered synonyms back. If any of these add nothing, move on.
 
 *Topic Scan* — Search for relevant terms. Read the most relevant existing artifact if one exists (brainstorm, plan, spec, skill, feature doc). Skim adjacent examples covering similar behavior.
 
@@ -210,6 +210,18 @@ Follow the Interaction Rules above. Use the platform's blocking question tool wh
 
 **Exit condition:** Continue until the idea is clear AND no integration-check questions are pending, OR the user explicitly wants to proceed.
 
+#### 1.4 Vocabulary Capture (only if CONCEPTS.md already exists)
+
+**Skip this sub-phase entirely if `CONCEPTS.md` does not exist at repo root** — creation is owned by ce-compound and ce-compound-refresh.
+
+If it exists, scan the dialogue for **resolved** domain terms — terms where the conversation actively pinned down a precise local meaning, not terms merely mentioned in passing. **Resolved means the dialogue is no longer questioning the definition.** Provisional terms that may still revise stay in the conversation only.
+
+For each resolved term: if missing, add it; if present but the dialogue surfaced new precision, refine it; if already consistent, no action.
+
+**Domain entities, named processes, and status concepts with project-specific meaning only.** Not file paths, class names, function signatures, or implementation decisions — `CONCEPTS.md` is a glossary, not a spec or catch-all.
+
+Follow the format set by existing entries. Apply edits silently.
+
 ### Phase 2: Explore Approaches
 
 If multiple plausible directions remain, propose **2-3 concrete approaches** based on research and conversation. Otherwise state the recommended direction directly.