diff --git a/README.md b/README.md
index ff9ef57..c623d41 100644
--- a/README.md
+++ b/README.md
@@ -140,6 +140,16 @@ KeiSeiKit ships 11 verified tool-bridge templates under `_bridges/`. Render them
 
 All paths are idempotent: existing bridge files in the project are skipped, never overwritten. See `_bridges/README.md` for the full template→output-path table.
 
+## Primitives
+
+`_primitives/` holds first-class building blocks that agents and pipelines depend on — executable utilities, not behavioral markdown. Currently one primitive ships with the kit:
+
+- `tomd` — universal non-native-format → markdown converter (PDF, DOCX, XLSX, PPTX, CSV, code, images with OCR). Ported from [KeiAgent](https://example.invalid/KeiAgent) with KeiSeiKit-style error tags and a configurable cache directory (`KEISEI_TOMD_CACHE`, default `/tmp/keisei-tomd-cache`).
+
+The matching hook `hooks/tomd-preread.sh` is a `PreToolUse(Read)` entry that auto-redirects Claude to a cached markdown conversion when a Read targets an opaque binary format — no agent has to know about `tomd` explicitly, but any agent that *does* need to shell out can invoke `~/.claude/agents/_primitives/tomd.sh report.pdf > report.md` directly.
+
+`/compose-solution` auto-discovers primitives: Phase 3's prior-art grep includes `_primitives/` so new composed artefacts can reference the existing converter instead of rolling their own.
+
 ## Meta-composer
 
 `/compose-solution` is the meta-creator: tell it what you want to solve in one free-text paragraph, it decomposes the task, greps existing blocks / skills / manifests / bridges for prior art, proposes a minimal math-first architecture, and assembles the right artefact — agent, skill, hook, rule, or block. Every decision except the intake is a click (option-picker), never free-text.
diff --git a/skills/compose-solution/phase-3-prior-art.md b/skills/compose-solution/phase-3-prior-art.md
index c417d45..fdd99f7 100644
--- a/skills/compose-solution/phase-3-prior-art.md
+++ b/skills/compose-solution/phase-3-prior-art.md
@@ -8,7 +8,7 @@ For EACH component from Phase 2, run three independent searches in parallel
 ```bash
 # Replace <keywords> with the component's 3-5 distinctive keywords as an
 # ERE alternation like (foo|bar|baz).
-grep -rinlE '<keywords>' _blocks/ _manifests/ skills/ _bridges/ hooks/ 2>/dev/null
+grep -rinlE '<keywords>' _blocks/ _manifests/ _primitives/ skills/ _bridges/ hooks/ 2>/dev/null
 ```
 
 ## 3b — Personal bundle reuse (conditional, skip on missing)
diff --git a/skills/compose-solution/phase-5-architecture.md b/skills/compose-solution/phase-5-architecture.md
index 947cdac..a938627 100644
--- a/skills/compose-solution/phase-5-architecture.md
+++ b/skills/compose-solution/phase-5-architecture.md
@@ -13,6 +13,12 @@ where block_* ∈ {_blocks/, newly drafted, skills/, _manifests/}
 invariant: <one-line, e.g. "every cube <200 LOC, every handoff verified">
 ```
 
+If the architecture requires parsing binary document formats (PDF / DOCX /
+XLSX / PPTX / CSV), reference the `tomd` primitive
+(`_primitives/tomd.sh`) instead of rolling custom parsing — RULE "reuse
+over rewrite". The PreToolUse(Read) hook `tomd-preread.sh` already redirects
+Claude to the converted markdown transparently.
+
 ## 5b — What is UNNECESSARY?
 
 For each block listed, justify why it's in. If a block can be removed