kushi-agents 5.4.2 → 5.4.4

package/README.md

@@ -218,6 +218,15 @@ The Evidence/ folder produced by every profile is a **stable public contract**
 | `apply-ado` | **preview** | n/a | Gated apply skill. v0.1.0-preview is dry-mode only (writes `planned.jsonl`); real ADO PATCH/POST lands in v0.1.x. |
 | `vertex-link` | **preview** | n/a | One-time link of a kushi project to a vertex repo `<customer>/<initiative>` (multi-binding supported). Populates `kushi.yaml#vertex`. Re-run with `--reconfigure` to change. |
 | `emit-vertex` | **preview** | n/a | Render vertex-shaped artifacts from kushi Evidence/+State/ — weekly status, decisions, workshops, comms, living-doc diff proposals. Stages first, validates against vertex's own schemas, applies on demand. |
+| `doctor` | core+ | n/a | v5.4.0 — Aggregated health check (env, self-check, evals, skill-checker, live-install drift, global wiki). `--json` for CI; `--strict` to fail on yellow. |
+| `lint` | standard+ | n/a | v5.1.0 — Run wiki-lint checks against `State/` (contradictions, stale claims, orphans, missing cross-refs, data gaps). Writes `State/reports/lint-YYYY-MM-DD.md`. |
+| `teach` | standard+ | n/a | v5.2.0 — Persist a reusable fact/preference/pattern under `.kushi/learnings/`. |
+| `explain` | standard+ | n/a | v5.2.0 — Retrieve a previously taught fact/preference/pattern from `.kushi/learnings/`. |
+| `promote` | standard+ | n/a | v5.3.0 — Copy a project State page into the global wiki at `~/.kushi-global/` with identifier redaction + back-link + dual log. Refuses without `--force` when identifiers detected. |
+| `migrate-files` | standard+ | n/a | v5.4.4 — One-time migration of root-level `bootstrap-status.md` / `FOLLOW-UPS.md` / `OPEN-QUESTIONS-DRAFT.md` to per-user `Evidence/<alias>/`. Dry-run by default; `--apply` to commit. Refuses to overwrite on content conflict. |
+| `global` (init/status/ask/lint) | standard+ | n/a | v5.3.0 — Manage the per-user cross-engagement wiki at `~/.kushi-global/State/`. |
+| `schema-evolve` | standard+ | n/a | v5.2.0 — Migrate `kushi.yaml` and Evidence/ layouts across schema versions; idempotent + dry-run by default. |
+| `create-skill` / `check-skill` | full | n/a | v5.0.4 — Skill-authoring harness (scaffold a new skill; lint/retrofit every SKILL.md against `skill-authoring.instructions.md`). |
 
 See [Quickstart](https://gim-home.github.io/kushi/getting-started/quickstart/) for the full workflow.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "kushi-agents",
-  "version": "5.4.2",
+  "version": "5.4.4",
   "description": "Install Kushi — multi-source project evidence agent with Comprehensive Structured Capture (CSC) into weekly-only files across Email, Teams, OneNote, Loop, SharePoint, Meetings, CRM, ADO. Meetings retain a sibling verbatim/ audit folder. WorkIQ-only for M365 sources (Graph / m365_* FORBIDDEN as fallbacks; user-paste is first-class). Host-agnostic.",
   "type": "module",
   "bin": {
@@ -41,7 +41,7 @@
   },
   "license": "MIT",
   "scripts": {
-    "test": "node --test src/check-workiq.test.mjs src/seed-config.test.mjs src/sanitize-workiq-input.test.mjs src/detect-vertex-repo.test.mjs src/vertex-validate.test.mjs src/emit-vertex.e2e.test.mjs src/config-root-resolve.test.mjs src/forbidden-workiq-phrasings.test.mjs src/multi-host-install.test.mjs src/eval-aggregator.test.mjs src/eval-runner.test.mjs src/skill-creator.test.mjs src/skill-checker.test.mjs src/hooks-dispatcher.test.mjs src/parallel-refresh.test.mjs src/otel-emit.test.mjs src/teach.test.mjs src/schema-evolve.test.mjs src/global-wiki.test.mjs src/promote.test.mjs src/doctor.test.mjs src/setup-wizard.test.mjs src/cli-no-args.test.mjs src/cli-no-args-tty.test.mjs",
+    "test": "node --test src/check-workiq.test.mjs src/seed-config.test.mjs src/sanitize-workiq-input.test.mjs src/detect-vertex-repo.test.mjs src/vertex-validate.test.mjs src/emit-vertex.e2e.test.mjs src/config-root-resolve.test.mjs src/forbidden-workiq-phrasings.test.mjs src/multi-host-install.test.mjs src/eval-aggregator.test.mjs src/eval-runner.test.mjs src/skill-creator.test.mjs src/skill-checker.test.mjs src/hooks-dispatcher.test.mjs src/parallel-refresh.test.mjs src/otel-emit.test.mjs src/teach.test.mjs src/schema-evolve.test.mjs src/global-wiki.test.mjs src/promote.test.mjs src/doctor.test.mjs src/setup-wizard.test.mjs src/cli-no-args.test.mjs src/cli-no-args-tty.test.mjs src/per-user-files.test.mjs",
     "test:integration:bootstrap": "node src/bootstrap-dryrun.integration.test.mjs",
     "smoke": "node scripts/smoke.mjs",
     "eval": "pwsh plugin/skills/eval/run-evals.ps1 -Skill",

package/plugin/agents/kushi.agent.md

@@ -57,6 +57,7 @@ The Evidence/ folder produced by `aggregate` is the **public contract** between
 | `@Kushi global init` / `status` / `ask <q>` / `lint` | standard+ | n/a | v5.3.0 — `global-wiki` — manage the per-user cross-engagement wiki at `~/.kushi-global/State/` (env `KUSHI_GLOBAL_ROOT` for tests). |
 | `@Kushi promote <project> <page>` | standard+ | n/a | v5.3.0 — `promote` — copy a project State page into the global wiki with identifier redaction + back-link + dual log. Refuses without `--force` when identifiers detected. |
 | `@Kushi doctor` | core+ | n/a (read-only) | v5.4.0 — `doctor` — aggregated health check (env, self-check, evals, skill-checker, live-install drift, global wiki). `--json` for CI; `--strict` to fail on yellow. |
+| `@Kushi migrate-files <project>` | standard+ | n/a | v5.4.4 — `migrate-per-user-files` — one-time migration of root-level `bootstrap-status.md` / `FOLLOW-UPS.md` / `OPEN-QUESTIONS-DRAFT.md` to per-user `Evidence/<alias>/`. Dry-run by default; `--apply` to commit. Refuses to overwrite on content conflict (`[needs-merge]`). |
 
 **Note on auto-routing**: `ask` does NOT require the `@Kushi ask` prefix. Any message that names a known project AND asks a question (what / who / when / status / summarize / etc.) auto-dispatches to `ask-project`. Producer verbs win in the unambiguous case.
 

package/plugin/instructions/bootstrap-status-format.instructions.md

@@ -5,7 +5,9 @@ excludeAgent: "code-review"
 
 # Bootstrap Status Artifact — Format Contract
 
-When `bootstrap-project` (or any full refresh / retry workflow) finishes a project run, it MUST write `<project>/bootstrap-status.md` using the format below. This file is the **fast orientation artifact** for the project — what was bootstrapped, what durable context now exists, what stage the engagement is in, what gaps remain. It is NOT a transcript of the run.
+When `bootstrap-project` (or any full refresh / retry workflow) finishes a project run, it MUST write `<project>/Evidence/<alias>/bootstrap-status.md` using the format below. This file is the **per-user fast orientation artifact** for the project — what was bootstrapped, what durable context now exists, what stage the engagement is in, what gaps remain. It is NOT a transcript of the run.
+
+> **v5.4.4+ — per-user path.** The bootstrap-status artifact is **per-user authored** under `Evidence/<alias>/bootstrap-status.md` per `multi-user-shared-files.instructions.md` § "Per-user authored files". A cross-contributor rollup lives at `<project>/_Consolidated/bootstrap-status.md`, written deterministically by `consolidate-evidence` (Step 5). The pre-v5.4.4 root-level `<project>/bootstrap-status.md` is owned by `consolidate-evidence` only; writers MUST NOT touch it. Legacy projects are auto-migrated by `migrate-per-user-files`.
 
 > **v4.4.2 contracts** — every `Status` cell in this artifact MUST come from the closed taxonomy in `status-taxonomy.instructions.md`. Direct-path failures that were recovered by a documented fallback MUST be rendered as `completed-via-fallback` per `fallback-status-reporting.instructions.md`, not `failed` / `blocked`. The pre-v4.4.2 ad-hoc strings (`populated`, `unsynced`, `degraded`, `partial-cap`, etc.) are mapped onto the taxonomy in `status-taxonomy.instructions.md §1`.
 
@@ -92,29 +94,28 @@ Use these exact strings everywhere (table cells, run-log, narrative):
 - `ado-not-complete` — engagement record not found yet OR ADO linkage missing
 - `completed-with-coverage-gaps` — final outcome with explicit gaps recorded
 
-## Multi-contributor safety (kushi v4.4.0+)
+## Multi-contributor safety (kushi v5.4.4+)
 
-`<project>/bootstrap-status.md` is shared across all contributors via OneDrive. Per `multi-user-shared-files.instructions.md`:
+Per `multi-user-shared-files.instructions.md`, this file is **per-user authored** at `<project>/Evidence/<alias>/bootstrap-status.md` and the consolidated cross-contributor view lives at `<project>/_Consolidated/bootstrap-status.md` (written by `consolidate-evidence` Step 5):
 
-1. **Before writing**, scan `<project>/` for sibling conflict copies (e.g. `bootstrap-status-conflict-<alias>-<host>.md` or OneDrive's `bootstrap-status (Stan's conflicted copy *)`). If any exist, merge their content into the canonical file (taking the most recent per-source row) and delete the conflict copies. Log this in the per-user bootstrap report under `## Conflict copies merged`.
-2. **Preserve other contributors' attribution.** Read the existing file; the `## Contributors who have bootstrapped this project` section MUST keep one row per alias that has ever written it. Update only the row matching the current alias.
-3. **Per-source rows** in `## Context Artifact Status` reflect the most recent discovery across all contributors. Add a trailing `Discovered by` column showing which alias performed the latest discovery (cross-referenced from each alias's `m365-mutable.json` via `Get-KushiConfig`).
-4. **The final one-line status** is for the most recent run only and may be overwritten by any contributor.
+1. **Writers target the per-user path only.** Every `bootstrap-project` / `refresh-project` run writes its own `Evidence/<alias>/bootstrap-status.md`. There is no read-modify-write contention — each alias owns its file.
+2. **No `Contributors who have bootstrapped this project` section on the per-user file.** That section is reconstructed in the `_Consolidated/bootstrap-status.md` rollup, which lists every contributor with their per-user file's `Last Run` / `Mode` / `Outcome`.
+3. **Conflict-copies on the per-user file are extremely rare** (only the owning alias writes it). If they do appear, the alias's next bootstrap absorbs them and deletes them per the universal merge rules.
+4. **The final one-line status** on the per-user file is for the most recent run by that alias only.
 
-### Required `## Contributors who have bootstrapped this project` section
+### Required `## Run summary` section on the per-user file
 
-Append this section immediately after `## Bootstrap Status`:
+Append immediately after `## Bootstrap Status`:
 
 ```
-## Contributors who have bootstrapped this project
+## Run summary
 
 | Alias | Display Name | Last Run | Mode | Outcome |
 |---|---|---|---|---|
-| ushak | Usha Kandregula | 2026-05-20 07:42 EDT | bootstrap | bootstrap-complete-with-coverage-gaps |
-| stand | Stan Doe       | 2026-05-18 16:01 EDT | refresh   | refresh-complete |
+| ushak | Usha Kandregula | 2026-05-27 09:42 EDT | bootstrap | bootstrap-complete-with-coverage-gaps |
 ```
 
-Preserve every existing row except the one matching your alias.
+`consolidate-evidence` Step 5 reads every `Evidence/<alias>/bootstrap-status.md`, harvests its `## Run summary` row, and emits a merged `## Contributors who have bootstrapped this project` table into `_Consolidated/bootstrap-status.md`.
 
 ## Sections to AVOID in bootstrap-status
 

package/plugin/instructions/multi-user-shared-files.instructions.md

@@ -1,87 +1,117 @@
----
-applyTo: "**/SKILL.md,**/*.prompt.md,**/Evidence/run-log.yml,**/integrations.yml,**/bootstrap-status.md,**/OPEN-QUESTIONS-DRAFT.md,**/State/09_open-questions.md,**/Evidence/contributors.yml"
----
-
-# Multi-user shared-file safety
-
-## Why this exists
-
-A Kushi engagement folder (`<engagement-root>/<project>/`) is shared across all contributors via OneDrive. Several artifacts inside it are **logically shared** — every contributor reads and writes the same path:
-
-| Shared artifact | Path | Writers |
-|---|---|---|
-| Per-project integrations | `<project>/integrations.yml` | `bootstrap-project`, `propose-ado-update`, `apply-ado-update`, every `pull-*` that discovers an ID |
-| Bootstrap status snapshot | `<project>/bootstrap-status.md` | `bootstrap-project` (every run, any contributor) |
-| Open questions draft | `<project>/OPEN-QUESTIONS-DRAFT.md` (or `State/09_open-questions.md` on full profile) | `bootstrap-project`, `consolidate-evidence`, `build-state`, `propose-ado-update` |
-| Run log | `<project>/Evidence/run-log.yml` | every `pull-*`, `bootstrap-project`, `refresh-project`, `fde-*` |
-| Contributors list | `<project>/Evidence/contributors.yml` | every `pull-*` (first time an alias touches the project) |
-
-Without rules, two contributors running concurrently produce one of:
-- OneDrive conflict-copy (`*-conflict-<alias>-<host>.yml`) — silent loss until manually merged.
-- Last-writer-wins overwrite — silent loss of the other contributor's data.
-
-This doctrine codifies the contract every writer must honor. It is **not** a substitute for proper locking, but it makes concurrent runs eventually consistent and recoverable.
-
-## Universal rules (apply to every shared artifact)
-
-1. **Read-modify-write, never blind-write.** Before writing any shared artifact, the skill MUST read the current file, merge its new contribution, and write the merged result. Blind overwrite is forbidden.
-2. **Detect and absorb conflict-copies.** Before reading the canonical file, glob for sibling files matching `<basename>-conflict-*` or `<basename> (<host>'s conflicted copy *)`. If any exist, merge their contents into the canonical file, then delete the conflict copies. Log the merge in the run report.
-3. **Stamp every contribution.** Every line / block / list-entry that a skill adds must carry its alias (from `project-evidence.yml`) and an ISO timestamp so future readers (and the merge logic above) can deterministically reconcile.
-4. **Idempotent appends.** Re-running the same skill in the same window MUST NOT duplicate prior entries. Use a `(alias, source, window_key)` tuple as the dedupe key.
-5. **Never delete another contributor's contribution.** A skill may only modify or remove entries it created (matched by alias). Cleanup of other aliases' entries is reserved for `consolidate-evidence`.
-
-## Per-artifact contracts
-
-### `<project>/integrations.yml`
-
-- **Pattern**: read-modify-write with alias stamp on changed fields.
-- Whenever a skill discovers a new ID (CRM `record_id`, ADO `engagement_id`, OneNote `section_file_id`, etc.), it MUST:
-  1. Read the current file.
-  2. If the target field is non-empty AND differs from the discovered value, write the discovered value into a sibling key `<field>_proposed_<alias>` and add a Q-row to `OPEN-QUESTIONS-DRAFT.md` for human reconciliation. Do not overwrite.
-  3. If the target field is empty (or matches), write the value and append a comment line: `# resolved by <alias> on <YYYY-MM-DD>` immediately above the changed key.
-- The `last_discovery_attempt` / `last_discovery_result` keys MAY be overwritten by any alias (they are intentionally last-writer-wins; the value is "the most recent attempt by anyone").
-
-### `<project>/bootstrap-status.md`
-
-- **Pattern**: full rewrite is permitted, but the file MUST carry a `## Contributors who have bootstrapped this project` section listing every alias that has ever written it, with their last-run timestamp.
-- Before rewriting, the skill MUST read the existing Contributors section and preserve every entry whose alias differs from the current alias. Update only its own alias row.
-- The per-source status tables (`OneNote`, `Email`, `Teams`, etc.) reflect the **most recent** discovery across all contributors. Skills MUST cross-reference `m365-mutable.json` (which is per-user) — when a row shows discovered IDs, also note which alias performed the discovery in a trailing `(by <alias>)` cell.
-
-### `<project>/OPEN-QUESTIONS-DRAFT.md` and `<project>/State/09_open-questions.md`
-
-- **Pattern**: append-only with dedup.
-- Every question row carries `[asked by <alias> on <YYYY-MM-DD>]` as the trailing column.
-- Before appending a new question, the skill MUST scan existing rows for a question whose normalized text (lowercased, whitespace-collapsed) matches. If a match exists, do not append a duplicate; instead, append `, <alias> on <date>` to the existing row's attribution.
-- Rows are removed only by an explicit `resolve-open-question` action (out of scope here) — never by another `bootstrap` / `refresh` run.
-
-### `<project>/Evidence/run-log.yml`
-
-- **Pattern**: structured append + max() merge.
-- Run history (`runs:` list) is append-only. Every entry carries `alias:` and `run_at:`.
-- Per-source watermarks (`sources.<source>.watermark`) use **max()** merge: when writing, the skill reads the current value and writes `max(current, new)`. Never overwrite with an older watermark.
-- Per-source errors (`sources.<source>.errors[]`) are append-only with `alias` + `at` on every entry; dedup on `(alias, code, at)`.
-
-### `<project>/Evidence/contributors.yml`
-
-- **Pattern**: append-only, alias-keyed.
-- The first time an alias runs against the project, append `{ alias, display_name, email, first_seen: <YYYY-MM-DD> }`. Subsequent runs MUST NOT modify the entry.
-- `last_seen` MAY be updated by any run, max()-merged.
-
-## Implementation guidance for skill authors
-
-- Read `<workspace>/.kushi/config/user/project-evidence.yml` to get your alias via `Get-KushiConfig -Name 'project-evidence'`. Never hardcode aliases.
-- For YAML merges, use `Get-Content -Raw | ConvertFrom-Yaml`, mutate, then `ConvertTo-Yaml`. Preserve comments where possible by line-based merging when structure permits.
-- For Markdown table merges in `OPEN-QUESTIONS-DRAFT.md`, parse the body to a list of rows, dedup by normalized question text, re-emit.
-- On any merge conflict the skill cannot resolve deterministically, write the alternative as a sibling-key `<field>_proposed_<alias>` (for YAML) or a `> Disagreement: <alias-A> says ..., <alias-B> says ...` callout (for Markdown) and add a Q-row to `OPEN-QUESTIONS-DRAFT.md`.
-
-## Out of scope
-
-- True file locking (filesystem advisory locks, OneDrive's checkout API) — relies on platform support Kushi can't assume.
-- Server-side merge service — Kushi is local-only by design.
-
-## Related doctrine
-
-- `evidence-layout-canonical.instructions.md` — what lives where under `Evidence/`.
-- `run-reports.instructions.md` — per-user run narrative (always under `Evidence/<alias>/`, no concurrency risk).
-- `bootstrap-status-format.instructions.md` — format contract for the shared status artifact.
-- `citation-ledger.instructions.md` — every assertion in shared artifacts must carry a citation; alias attribution is the citation for shared-file entries.
+---
+applyTo: "**/SKILL.md,**/*.prompt.md,**/Evidence/run-log.yml,**/integrations.yml,**/bootstrap-status.md,**/FOLLOW-UPS.md,**/OPEN-QUESTIONS-DRAFT.md,**/Evidence/*/bootstrap-status.md,**/Evidence/*/FOLLOW-UPS.md,**/Evidence/*/OPEN-QUESTIONS-DRAFT.md,**/_Consolidated/bootstrap-status.md,**/_Consolidated/FOLLOW-UPS.md,**/_Consolidated/OPEN-QUESTIONS-DRAFT.md,**/State/09_open-questions.md,**/Evidence/contributors.yml"
+---
+
+# Multi-user shared-file safety
+
+## Why this exists
+
+A Kushi engagement folder (`<engagement-root>/<project>/`) is shared across all contributors via OneDrive. Some artifacts inside it are **logically shared** — every contributor reads and writes the same path. Others are **per-user authored** — every contributor writes their own copy under `Evidence/<alias>/` and `consolidate-evidence` later merges them into `_Consolidated/`.
+
+| Shared artifact | Path | Writers |
+|---|---|---|
+| Per-project integrations | `<project>/integrations.yml` | `bootstrap-project`, `propose-ado-update`, `apply-ado-update`, every `pull-*` that discovers an ID |
+| Run log | `<project>/Evidence/run-log.yml` | every `pull-*`, `bootstrap-project`, `refresh-project`, `fde-*` |
+| Contributors list | `<project>/Evidence/contributors.yml` | every `pull-*` (first time an alias touches the project) |
+| Project config | `<project>/kushi.yaml`, `<project>/.settings.yml` | `setup`, `bootstrap-project` |
+
+Without rules, two contributors running concurrently produce one of:
+- OneDrive conflict-copy (`*-conflict-<alias>-<host>.yml`) — silent loss until manually merged.
+- Last-writer-wins overwrite — silent loss of the other contributor''s data.
+
+This doctrine codifies the contract every writer must honor. It is **not** a substitute for proper locking, but it makes concurrent runs eventually consistent and recoverable.
+
+## Per-user authored files (v5.4.4+)
+
+Three artifacts that historically lived at the project root are now **per-user authored** with an auto-generated consolidated view. v5.4.3 soak finding #5: every contributor''s `bootstrap-project` run was overwriting the previous contributor''s `<project>/bootstrap-status.md`, silently losing truth.
+
+| File | Per-user path (truth) | Consolidated path (auto-generated by `consolidate-evidence`) |
+|---|---|---|
+| `bootstrap-status.md` | `<project>/Evidence/<alias>/bootstrap-status.md` | `<project>/_Consolidated/bootstrap-status.md` |
+| `FOLLOW-UPS.md` | `<project>/Evidence/<alias>/FOLLOW-UPS.md` | `<project>/_Consolidated/FOLLOW-UPS.md` |
+| `OPEN-QUESTIONS-DRAFT.md` | `<project>/Evidence/<alias>/OPEN-QUESTIONS-DRAFT.md` | `<project>/_Consolidated/OPEN-QUESTIONS-DRAFT.md` |
+
+**Rules:**
+
+1. **Writers target the per-user path only.** `bootstrap-project`, `refresh-project`, `aggregate-project`, every `pull-*` (for `OPEN-QUESTIONS-DRAFT.md` rows they append), `propose-ado-update`, and the per-source verification gate (for `FOLLOW-UPS.md` rows) all write to `<project>/Evidence/<alias>/<file>`. The alias is resolved from `.kushi/config/user/project-evidence.yml` via `Get-KushiConfig -Name ''project-evidence''`. Writers MUST NOT touch the project-root copies — those are owned by `consolidate-evidence`, which writes to `_Consolidated/`.
+2. **`consolidate-evidence` owns the `_Consolidated/` copies.** After per-user files are written, `consolidate-evidence` (called either directly, or transitively from `aggregate-project` / `refresh-project`) emits `<project>/_Consolidated/<file>` from every contributor''s `Evidence/<alias>/<file>`. Deterministic merge — no LLM. Idempotent.
+3. **The root-level copies are NEVER written by hand or by skills going forward.** Legacy projects may still carry root-level `bootstrap-status.md` / `FOLLOW-UPS.md` / `OPEN-QUESTIONS-DRAFT.md` from pre-v5.4.4 runs; the `migrate-per-user-files` skill moves them to `Evidence/<alias>/` on first opportunity. See `plugin/skills/migrate-per-user-files/SKILL.md`.
+4. **Readers MAY read both.** Q&A / dashboard / FDE-report skills SHOULD prefer `_Consolidated/<file>` when present; fall back to merging every `Evidence/<alias>/<file>` themselves if the consolidated copy is stale.
+
+### Per-user `bootstrap-status.md`
+
+- Full rewrite by its owning alias only. Other aliases'' files are untouched.
+- The `## Contributors who have bootstrapped this project` section is no longer required on the per-user file — each alias''s file represents only that alias''s bootstrap state. The consolidated copy at `_Consolidated/bootstrap-status.md` reconstructs the cross-contributor section.
+
+### Per-user `FOLLOW-UPS.md`
+
+- Append-only by its owning alias under `Evidence/<alias>/FOLLOW-UPS.md`. Open / Resolved sections per `per-source-verification-gate.instructions.md` §B (5-field shape). Auto-resolution flips `Status: open` → `resolved-<YYYY-MM-DD>` on the alias''s next run when the gate passes. Consolidated rollup at `_Consolidated/FOLLOW-UPS.md`.
+
+### Per-user `OPEN-QUESTIONS-DRAFT.md`
+
+- Append-only at `Evidence/<alias>/OPEN-QUESTIONS-DRAFT.md`, dedup by normalized question text within the alias''s own file. Every row carries `[asked by <alias> on <YYYY-MM-DD>]`.
+- Rows are removed only by an explicit `resolve-open-question` action — never by another `bootstrap` / `refresh` run. Cross-contributor rollup at `_Consolidated/OPEN-QUESTIONS-DRAFT.md`.
+
+### Auto-consolidation merge contract
+
+`consolidate-evidence` emits three deterministic files under `_Consolidated/` (see `plugin/skills/consolidate-evidence/SKILL.md` Step 5):
+
+- **`_Consolidated/bootstrap-status.md`** — header + per-contributor sub-section (verbatim copy of each `Evidence/<alias>/bootstrap-status.md`) + a merged "Latest discovery sweep results" table preferring most-recent-resolved per source.
+- **`_Consolidated/FOLLOW-UPS.md`** — dedup-merged rows tagged with originating `(alias)`. Dedup key is the source + first line of "Next-time-do".
+- **`_Consolidated/OPEN-QUESTIONS-DRAFT.md`** — questions deduped by normalized text, with an attribution column listing every alias that asked it and the earliest date.
+
+Re-running `consolidate-evidence` is idempotent. Output is byte-stable for the same input set.
+
+## Universal rules (apply to every shared artifact)
+
+1. **Read-modify-write, never blind-write.** Before writing any shared artifact, the skill MUST read the current file, merge its new contribution, and write the merged result. Blind overwrite is forbidden.
+2. **Detect and absorb conflict-copies.** Before reading the canonical file, glob for sibling files matching `<basename>-conflict-*` or `<basename> (<host>''s conflicted copy *)`. If any exist, merge their contents into the canonical file, then delete the conflict copies. Log the merge in the run report.
+3. **Stamp every contribution.** Every line / block / list-entry that a skill adds must carry its alias (from `project-evidence.yml`) and an ISO timestamp so future readers (and the merge logic above) can deterministically reconcile.
+4. **Idempotent appends.** Re-running the same skill in the same window MUST NOT duplicate prior entries. Use a `(alias, source, window_key)` tuple as the dedupe key.
+5. **Never delete another contributor''s contribution.** A skill may only modify or remove entries it created (matched by alias). Cleanup of other aliases'' entries is reserved for `consolidate-evidence`.
+
+## Per-artifact contracts (truly shared root files)
+
+### `<project>/integrations.yml`
+
+- **Pattern**: read-modify-write with alias stamp on changed fields.
+- Whenever a skill discovers a new ID (CRM `record_id`, ADO `engagement_id`, OneNote `section_file_id`, etc.), it MUST:
+  1. Read the current file.
+  2. If the target field is non-empty AND differs from the discovered value, write the discovered value into a sibling key `<field>_proposed_<alias>` and add a Q-row to the alias''s `Evidence/<alias>/OPEN-QUESTIONS-DRAFT.md` for human reconciliation. Do not overwrite.
+  3. If the target field is empty (or matches), write the value and append a comment line: `# resolved by <alias> on <YYYY-MM-DD>` immediately above the changed key.
+- The `last_discovery_attempt` / `last_discovery_result` keys MAY be overwritten by any alias (they are intentionally last-writer-wins; the value is "the most recent attempt by anyone").
+
+### `<project>/Evidence/run-log.yml`
+
+- **Pattern**: structured append + max() merge.
+- Run history (`runs:` list) is append-only. Every entry carries `alias:` and `run_at:`.
+- Per-source watermarks (`sources.<source>.watermark`) use **max()** merge: when writing, the skill reads the current value and writes `max(current, new)`. Never overwrite with an older watermark.
+- Per-source errors (`sources.<source>.errors[]`) are append-only with `alias` + `at` on every entry; dedup on `(alias, code, at)`.
+
+### `<project>/Evidence/contributors.yml`
+
+- **Pattern**: append-only, alias-keyed.
+- The first time an alias runs against the project, append `{ alias, display_name, email, first_seen: <YYYY-MM-DD> }`. Subsequent runs MUST NOT modify the entry.
+- `last_seen` MAY be updated by any run, max()-merged.
+
+## Implementation guidance for skill authors
+
+- Read `<workspace>/.kushi/config/user/project-evidence.yml` to get your alias via `Get-KushiConfig -Name ''project-evidence''`. Never hardcode aliases.
+- For per-user files (`bootstrap-status.md`, `FOLLOW-UPS.md`, `OPEN-QUESTIONS-DRAFT.md`), write under `<project>/Evidence/<alias>/<file>`. Path-scope hint near every literal mention: `Evidence/<alias>/` or `_Consolidated/`.
+- For YAML merges of shared root files, use `Get-Content -Raw | ConvertFrom-Yaml`, mutate, then `ConvertTo-Yaml`. Preserve comments where possible by line-based merging when structure permits.
+- For Markdown table merges in per-user `OPEN-QUESTIONS-DRAFT.md`, parse the body to a list of rows, dedup by normalized question text, re-emit.
+- On any merge conflict the skill cannot resolve deterministically, write the alternative as a sibling-key `<field>_proposed_<alias>` (for YAML) or a `> Disagreement: <alias-A> says ..., <alias-B> says ...` callout (for Markdown) and add a Q-row to `<project>/Evidence/<alias>/OPEN-QUESTIONS-DRAFT.md`.
+
+## Out of scope
+
+- True file locking (filesystem advisory locks, OneDrive''s checkout API) — relies on platform support Kushi can''t assume.
+- Server-side merge service — Kushi is local-only by design.
+
+## Related doctrine
+
+- `evidence-layout-canonical.instructions.md` — what lives where under `Evidence/`.
+- `run-reports.instructions.md` — per-user run narrative (always under `Evidence/<alias>/`, no concurrency risk).
+- `bootstrap-status-format.instructions.md` — format contract for the per-user bootstrap-status artifact.
+- `citation-ledger.instructions.md` — every assertion in shared artifacts must carry a citation; alias attribution is the citation for shared-file entries.
+- `plugin/skills/consolidate-evidence/SKILL.md` — Step 5 (v5.4.4+) emits the `_Consolidated/` copies of the per-user authored files.
+- `plugin/skills/migrate-per-user-files/SKILL.md` — one-time migration from root-level legacy paths to `Evidence/<alias>/`.

package/plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "kushi",
   "description": "Multi-source project evidence + Q&A agent. Snapshot + stream capture across Email, Teams, OneNote, Loop, SharePoint, Meetings, CRM, ADO; plus read-only natural-language Q&A over the captured evidence. WorkIQ-only for M365 sources (Graph / m365_* FORBIDDEN as fallbacks; user-paste is first-class). Host-agnostic. Three install profiles: core (aggregator only), standard (default — adds bootstrap/refresh + FDE authoring), full (adds State/ rollup).",
-  "version": "3.15.0",
+  "version": "3.16.0",
   "author": "ushakrishnan",
   "repository": "https://github.com/gim-home/kushi",
   "default_profile": "standard",
@@ -11,6 +11,8 @@
       "skills": [
         "intro",
         "self-check",
+        "doctor",
+        "eval",
         "setup",
         "pull-email",
         "pull-teams",
@@ -18,6 +20,7 @@
         "pull-onenote",
         "pull-loop",
         "pull-sharepoint",
+        "pull-misc",
         "pull-crm",
         "pull-ado",
         "aggregate-project",
@@ -34,7 +37,8 @@
         "status",
         "ask",
         "vertex-link",
-        "emit-vertex"
+        "emit-vertex",
+        "doctor"
       ],
       "instructions": "*",
       "templates": [
@@ -50,7 +54,8 @@
         "pull",
         "ask",
         "vertex-link",
-        "emit-vertex"
+        "emit-vertex",
+        "doctor"
       ]
     },
     "standard": {
@@ -64,7 +69,12 @@
         "fde-triage",
         "link-entities",
         "dashboard",
-        "tour"
+        "tour",
+        "lint-state",
+        "teach",
+        "promote",
+        "schema-evolve",
+        "migrate-per-user-files"
       ],
       "prompts": [
         "bootstrap",
@@ -74,7 +84,8 @@
         "fde-triage",
         "link-entities",
         "dashboard",
-        "tour"
+        "tour",
+        "migrate-files"
       ],
       "templates": [
         "init",
@@ -92,15 +103,24 @@
         "fde-triage",
         "link-entities",
         "dashboard",
-        "tour"
+        "tour",
+        "lint",
+        "teach",
+        "explain",
+        "promote",
+        "schema-evolve",
+        "migrate-files"
       ],
       "_": null
     },
     "full": {
       "extends": "standard",
-      "description": "Standard + State/ rollup. Adds the opinionated outcome-based State/ files (decisions, stakeholders, architecture, action items, risks, timeline, artifacts, open questions) built on top of Evidence/. On this profile, bootstrap/refresh call build-state at the end.",
+      "description": "Standard + State/ rollup + global cross-engagement wiki + skill-authoring harness. Adds the opinionated outcome-based State/ files (decisions, stakeholders, architecture, action items, risks, timeline, artifacts, open questions) built on top of Evidence/, plus ~/.kushi-global/ wiki tooling and skill-creator/skill-checker for contributors. On this profile, bootstrap/refresh call build-state at the end.",
       "skills": [
-        "build-state"
+        "build-state",
+        "global-wiki",
+        "skill-creator",
+        "skill-checker"
       ],
       "prompts": [
         "state"
@@ -110,7 +130,10 @@
       ],
       "reference_packs": [],
       "verbs": [
-        "state"
+        "state",
+        "global",
+        "create-skill",
+        "check-skill"
       ]
     },
     "preview": {

package/plugin/prompts/bootstrap.prompt.md

@@ -59,7 +59,8 @@ Produces:
 - `<engagement-root>/<project>/integrations.yml` (per-project boundaries + enabled-sources, shared via OneDrive)
 - `<engagement-root>/<project>/Evidence/{contributors.yml, run-log.yml, <alias>/.settings.yml, <alias>/{email,teams,meetings,onenote,sharepoint,crm,ado}/{snapshot,stream}/, <alias>/_deferred-retries/}`
 - `<engagement-root>/<project>/State/{00..09}_*.md` (full profile only)
-- `<engagement-root>/<project>/bootstrap-status.md` (shared, multi-user safe)
+- `<engagement-root>/<project>/Evidence/<alias>/bootstrap-status.md` (per-user authored, v5.4.4+ — auto-consolidated to `<project>/_Consolidated/bootstrap-status.md` by `consolidate-evidence`)
+- `<engagement-root>/<project>/Evidence/<alias>/FOLLOW-UPS.md` and `<engagement-root>/<project>/Evidence/<alias>/OPEN-QUESTIONS-DRAFT.md` (per-user authored, v5.4.4+ — auto-consolidated under `_Consolidated/`)
 
 Delegates to `bootstrap-project` skill. After scaffolding, calls each `pull-<source>` skill, then `build-state` (full profile only).
 

package/plugin/prompts/consolidate.prompt.md

@@ -24,7 +24,10 @@ Reads:
 - `<engagement-root>/<project>/Evidence/contributors.yml`
 
 Writes:
-- `<engagement-root>/<project>/Evidence/_Consolidated/<YYYY-MM-DD>_consolidated.md` (Monday of the week)
+- `<engagement-root>/<project>/Evidence/_Consolidated/<YYYY-MM-DD>_consolidated.md` (Monday of the week — per-source CSC rollups)
+- `<engagement-root>/<project>/_Consolidated/bootstrap-status.md` (v5.4.4+ — rollup of every `Evidence/<alias>/bootstrap-status.md`)
+- `<engagement-root>/<project>/_Consolidated/FOLLOW-UPS.md` (v5.4.4+ — rollup of every `Evidence/<alias>/FOLLOW-UPS.md`)
+- `<engagement-root>/<project>/_Consolidated/OPEN-QUESTIONS-DRAFT.md` (v5.4.4+ — rollup of every `Evidence/<alias>/OPEN-QUESTIONS-DRAFT.md`)
 
 Provenance tags retained (source: <alias>/<source>/<file>) per `citation-ledger.instructions.md`.
 

package/plugin/prompts/create-skill.prompt.md

@@ -0,0 +1,26 @@
+---
+name: create-skill
+description: "Scaffold a new kushi skill from the skill-creator harness."
+argument-hint: "Skill name + optional --description '...'. Example: 'create-skill pull-confluence'."
+agent: kushi
+tools: [search, read/readFile, edit, 'execute/runInTerminal', agent]
+---
+
+## User Input
+
+```text
+${input:name_and_flags:Skill name + optional flags, e.g. 'pull-confluence --description "Pull from Confluence"'}
+```
+
+# /create-skill
+
+Route to `@Kushi create-skill <name>`.
+
+Scaffolds a new skill under `plugin/skills/<name>/` with SKILL.md frontmatter,
+description placeholder, references/ folder, and example test stub. Output
+conforms to `skill-authoring.instructions.md` so `check-skill` passes on first
+run.
+
+Companion verb: `/check-skill <name>` lints + retrofits an existing skill.
+
+Delegates to `skill-creator` skill.

package/plugin/prompts/doctor.prompt.md

@@ -0,0 +1,31 @@
+---
+name: doctor
+description: "Aggregated health check — env, self-check, evals, skill-checker, install drift, global wiki."
+argument-hint: "No project needed; runs system-wide diagnostics. Flags: --json (CI), --strict (fail on yellow)."
+agent: kushi
+tools: [search, read/readFile, 'execute/runInTerminal', agent]
+---
+
+## User Input
+
+```text
+${input:flags:Optional flags (--json, --strict). Empty for human-readable run.}
+```
+
+# /doctor
+
+Route to `@Kushi doctor` — aggregated health check covering:
+
+- **env** — node, pwsh, kushi version, install layout
+- **self-check** `-Deep` — D1..D41 doctrine checks
+- **evals** `:canary` — golden-set regression check
+- **skill-checker** `-All` — every SKILL.md against `skill-authoring.instructions.md`
+- **live-install drift** — repo source vs installed `~/.copilot/m-skills/kushi/` and `~/.vscode/chat/skills/kushi/`
+- **global wiki** — `~/.kushi-global/State/` shape + run-log
+
+Output: colored ribbon (GREEN / YELLOW / RED) + per-finding fix.
+
+Read-only by default. No pulls, no writes.
+
+Delegates to the `doctor` skill (`skills/doctor/doctor.ps1`). For CI:
+`pwsh -File skills/doctor/doctor.ps1 --json --strict`.

package/plugin/prompts/explain.prompt.md

@@ -0,0 +1,22 @@
+---
+name: explain
+description: "Retrieve a previously taught fact / preference / pattern from .kushi/learnings/."
+argument-hint: "Topic. Example: 'explain HCA naming-convention'."
+agent: kushi
+tools: [search, read/readFile, agent]
+---
+
+## User Input
+
+```text
+${input:topic:Topic, e.g. 'HCA naming-convention'}
+```
+
+# /explain
+
+Route to `@Kushi explain <topic>`.
+
+Looks up `.kushi/learnings/<slug>.md` (or fuzzy-match by topic substring) and renders
+the body + history. Read-only — never mutates the learning. Companion to `/teach`.
+
+Delegates to `teach` skill (explain mode).

package/plugin/prompts/global.prompt.md

@@ -0,0 +1,28 @@
+---
+name: global
+description: "Manage the per-user cross-engagement wiki at ~/.kushi-global/State/."
+argument-hint: "Sub-verb: init | status | ask <question> | lint. Example: 'global ask what's our default pull window?'"
+agent: kushi
+tools: [search, read/readFile, edit, agent]
+---
+
+## User Input
+
+```text
+${input:subverb_and_args:Sub-verb + args, e.g. 'init', 'status', 'ask what's our default pull window?', 'lint'}
+```
+
+# /global
+
+Route to `@Kushi global <sub-verb>`.
+
+Manages the cross-engagement wiki at `~/.kushi-global/State/` (override with
+`KUSHI_GLOBAL_ROOT` for tests). Sub-verbs:
+
+- `init` — scaffold the global wiki layout (decisions/, patterns/, glossary/, run-log).
+- `status` — show last-promoted pages + recent activity from the dual log.
+- `ask <q>` — citation-only Q&A over the global wiki (mirrors `kushi ask <project>` shape).
+- `lint` — wiki-lint over the global wiki (same checks as project lint).
+
+Delegates to `global-wiki` skill. Companion verb: `/promote` copies a project
+page up into the global wiki with identifier redaction.

package/plugin/prompts/lint.prompt.md

@@ -0,0 +1,28 @@
+---
+name: lint
+description: "Run wiki-lint checks against State/ — contradictions, stale claims, orphans, gaps."
+argument-hint: "Project name; runs against <project>/State/ and writes State/reports/lint-YYYY-MM-DD.md"
+agent: kushi
+tools: [search, read/readFile, edit, agent]
+---
+
+## User Input
+
+```text
+${input:project:Project name, e.g. HCA}
+```
+
+# /lint
+
+Route to `@Kushi lint <project>`.
+
+Runs the v5.1.0 `lint-state` skill against `<engagement-root>/<project>/State/`:
+- contradiction detection (claim A vs claim B with same subject)
+- stale claims (>14d without source-evidence freshness)
+- orphan pages (no inbound cross-refs)
+- missing required cross-refs per page type
+- data gaps (entities referenced but not pulled)
+
+Writes `<project>/State/reports/lint-YYYY-MM-DD.md`. Read-only against Evidence/.
+
+Delegates to `lint-state` skill.