gm-kilo 2.0.892 → 2.0.894

package/agents/memorize.md

@@ -51,6 +51,8 @@ exec:memorize
 
 Line 1 of the body is the source tag (e.g. `feedback/terse-responses`, `project/merge-freeze`). Lines 2+ are the fact itself. Use kebab-case slugs.
 
+A discipline sigil — `@<name>` as the first space-token in the invoking prompt, or a trailing `discipline=<name>` line — routes the write to that discipline's store. Without one, the write lands in the default store. Forward the sigil verbatim to `exec:memorize`; never invent or default a discipline name.
+
 To invalidate previously-memorized content (correction or retraction):
 
 ```

package/agents/research-worker.md

@@ -9,6 +9,8 @@ allowed-tools: WebFetch, WebSearch, Bash
 
 One question. One context. One file on disk. One-line return.
 
+Two shapes of brief arrive: a live-web question owning a path under `.gm/research/<slug>/<worker-id>.md`, or a corpus chunk owning `.gm/disciplines/<name>/corpus/concise/<chunk-id>.md`. The corpus shape carries an input chunk on disk and a fact-preservation contract — every claim, number, name, caveat, and citation from the source survives the rewrite; prose density rises, content does not shrink. No fetching unless the brief asks for it. The output file looks like the live-web one but the `Sources` section points at the input chunk path and any inline citations the chunk already carried.
+
 ## Brief shape
 
 The spawning prompt names: the question, the answer shape expected, the explicit out-of-scope boundary, and the destination path `.gm/research/<slug>/<worker-id>.md`. If any of those is missing or ambiguous, treat that as the first finding — record what was unclear and stop, rather than guessing scope.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-kilo",
-  "version": "2.0.892",
+  "version": "2.0.894",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",

package/skills/code-search/SKILL.md

@@ -7,6 +7,8 @@ description: Mandatory codebase search workflow. Use whenever you need to find a
 
 `exec:codesearch` is the only codebase search tool. Grep, Glob, Find, Explore, raw `grep`/`rg`/`find` inside `exec:bash` are all hook-blocked. No fallback.
 
+A `@<discipline>` first-token after the verb scopes the search to that discipline's index; absent the sigil, results fan across default plus enabled disciplines, prefixed by source.
+
 Handles exact symbols, exact strings, file-name fragments, regex-ish patterns, natural-language queries, and PDF pages (cite `path/doc.pdf:<page>`).
 
 Direct-read exceptions: known absolute path → `Read`. Known directory listing → `exec:nodejs` + `fs.readdirSync`.

package/skills/gm-execute/SKILL.md

@@ -7,6 +7,8 @@ description: EXECUTE phase AND the foundational execution contract for every ski
 
 Entry: `.prd` with named unknowns. Exit: every mutable KNOWN → invoke `gm-emit`.
 
+A `@<discipline>` sigil propagates from PLAN through every recall, codesearch, and memorize call; reads without one fan across default plus enabled disciplines, writes without one go to default only.
+
 This skill is the execution contract for ALL phases — pre-emit witnesses, post-emit verifies, e2e checks all run on this discipline. Cross-cutting dispositions live in `gm` SKILL.md.
 
 ## Transitions

package/skills/planning/SKILL.md

@@ -8,6 +8,8 @@ allowed-tools: Skill, Bash, Write, Read, Agent
 
 Translate the request into `.gm/prd.yml` and hand to `gm-execute`. Re-enter on any new unknown in any phase.
 
+A `@<discipline>` sigil in the request scopes recall, codesearch, and memorize calls during PLAN to that discipline's store. Without one, retrievals fan across default plus enabled disciplines and writes land in default only.
+
 Cross-cutting dispositions (autonomy, fix-on-sight, nothing-fake, browser-witness, scope, recall, memorize) live in `gm` SKILL.md; this skill only carries what is unique to PLAN.
 
 ## Transitions

package/skills/research/SKILL.md

@@ -6,8 +6,12 @@ allowed-tools: Skill, Bash, Agent, WebFetch, WebSearch, Read, Write
 
 # Research
 
+Declare the discipline before fetching anything. The first line of work names the `@<discipline>` the corpus belongs to — fresh material lives at `.gm/disciplines/<name>/corpus/raw/`, concise rewrites at `.gm/disciplines/<name>/corpus/concise/<chunk-id>.md`, the merged synthesis at `.gm/disciplines/<name>/deep-understanding.md`. A run without a discipline declaration falls back to the default store and the orchestrator says so in one line.
+
 Lead orchestrates. Workers fetch. Findings converge on disk. The lead never reads pages — workers do.
 
+Treat a thousand-document corpus with the same care as a codebase. Material above roughly ten pages — about eight thousand tokens — splits at paragraph boundaries into chunks each owned by one parallel `gm:research-worker` (haiku model). Each worker emits a fact-preserving concise rewrite to `corpus/concise/<chunk-id>.md` — every claim, number, name, caveat from the source survives, prose density rises, citations stay attached. Once every chunk returns, the lead merges into `deep-understanding.md` enumerating the opportunities the corpus opens and the reasonable opinionations it forces. Concise files and the merged document auto-ingest via `exec:memorize @<name>` so the next pass recalls instead of re-fetching.
+
 Effort matches stakes. A single fact is one short fetch. A vendor comparison is a handful of workers, each owning one vendor. A landscape survey is ten or more, each owning one axis. Spending a fan-out on a fact wastes tokens; spending a fact-fetch on a landscape under-delivers.
 
 Breadth first, depth on demand. Open with a wide sweep that maps the terrain, then commit deep dives only where the sweep surfaces something load-bearing. A narrow opening misses the alternative the user actually needed.