@event4u/agent-config 6.0.0 → 7.0.0

package/dist/agent-src/commands/threat-model.md

@@ -3,6 +3,7 @@ model_tier: high
 name: threat-model
 pack: engineering-base
 tier: 2
+visibility: internal
 skills: [threat-modeling, authz-review, security-sensitive-stop]
 description: Run a pre-implementation threat model on a proposed change — enumerates abuse cases, trust boundaries, and authorization gaps before the first line of code is written
 council_depth: deep
@@ -78,7 +79,7 @@ Produce one combined report with these sections, in order:
 5. **Required controls** — the minimum set of validations, authorization
    checks, logging, and negative tests that must exist before the change ships
 6. **Open questions** — anything the skills flagged as uncertain and the user
-   must answer before impl starts
+   must answer before implementation starts
 
 ### 5. Decide next step
 
@@ -90,7 +91,7 @@ After the report, ask:
 > 3. Stop here — threat model is the deliverable, no implementation yet
 ```
 
-- On **1**: hand off to the impl flow (e.g., `feature-plan`,
+- On **1**: hand off to the implementation flow (e.g., `feature-plan`,
   `bug-fix`, or direct edit) with the required-controls list pinned
 - On **2**: re-gather context and re-dispatch
 - On **3**: save the report as the deliverable, stop
@@ -113,7 +114,7 @@ After the report, ask:
 - NEVER merge `threat-modeling` and `authz-review` outputs into a single
   block — each skill owns its format
 - NEVER write production code in the same turn as this command — the
-  deliverable is the report; impl is a separate step
+  deliverable is the report; implementation is a separate step
 - NEVER mark the change "safe" if any 🔴 abuse case has no control
 
 ## See also
@@ -123,4 +124,4 @@ After the report, ask:
 - [`data-flow-mapper`](../skills/data-flow-mapper/SKILL.md) — trace specific data through the change
 - [`blast-radius-analyzer`](../skills/blast-radius-analyzer/SKILL.md) — enumerate affected call sites
 - [`security-sensitive-stop`](../rules/security-sensitive-stop.md) — the trigger rule
-- [`minimal-safe-diff`](../rules/minimal-safe-diff.md) — keep the impl scoped
+- [`minimal-safe-diff`](../rules/minimal-safe-diff.md) — keep the implementation scoped

package/dist/agent-src/commands/update-form-request-messages.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: update-form-request-messages
 pack: engineering-base
 tier: 2
+visibility: internal
 framework: laravel
 skills: [laravel-validation]
 description: "Sync the messages() method of a FormRequest class — add missing entries, link them to language keys, and clean up stale ones."

package/dist/agent-src/commands/upstream-contribute.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: upstream-contribute
 pack: meta
 tier: 2
+visibility: internal
 skills: [upstream-contribute, skill-writing, learning-to-rule-or-skill]
 description: Contribute a learning, skill, rule, or fix from a consumer project back to the shared agent-config package
 suggestion:
@@ -125,9 +126,9 @@ Frontmatter must have `source: package`.
 ### 6. Run quality gates
 
 ```bash
-python3 scripts/skill_linter.py --all           # 0 FAIL required
-python3 scripts/check_condensation.py            # No 🔴 errors for this file
-python3 scripts/condense.py --generate-tools    # Regenerate symlinks
+./scripts-run src/scripts/skill_linter --all           # 0 FAIL required
+./scripts-run src/scripts/check_condensation            # No 🔴 errors for this file
+./scripts-run src/scripts/condense --generate-tools    # Regenerate symlinks
 bash scripts/condense.sh --check                # dist/agent-src/ in sync with source
 bash scripts/condense.sh --check-hashes         # All hashes match
 ```

package/dist/agent-src/commands/video/from-script.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-from-script
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: from-script
 description: Drive a script end-to-end through the AI video pipeline — scenes → blueprint → image → operator pick → motion → video → stitch. Preview default; --mode commit spends behind the cost gate.
@@ -56,7 +57,7 @@ call has happened yet.
 
 ### 2. Load config + resolve providers
 
-Source `scripts/ai-video/lib/load-config.sh`. Resolve image / video
+Source `scripts/media/lib/load-config.sh`. Resolve image / video
 provider in this order: command flag → `agents/.ai-video.xml` default
 → fail with the available-providers list.
 
@@ -155,4 +156,4 @@ cost (commit) or summed modeled `cost_estimate` labeled *modeled*
 - [`/video:scene`](scene.md) — single-scene iteration
 - [`/video:storyboard`](storyboard.md) — image-only contact sheet
 - [`/video:stitch`](stitch.md) — re-stitch after operator edits
-- [`scripts/ai-video/lib/adapter-contract.md`](../../../scripts/ai-video/lib/adapter-contract.md)
+- [`scripts/media/lib/adapter-contract.md`](../../../scripts/media/lib/adapter-contract.md)

package/dist/agent-src/commands/video/from-song.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-from-song
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: from-song
 description: Music-video from a song + reference images — accept or derive a timed scene script, optional character-lock, render, stitch, mux song as master track. Preview default; --mode commit gates the spend.
@@ -80,7 +81,7 @@ absent from `dist/agent-src/personas/` or `dist/agent-src/skills/`. No network
 call has happened yet.
 
 Then confirm the **runtime helper scripts** exist and are executable —
-`scripts/ai-video/lib/probe-audio.sh`, `scripts/ai-video/lib/load-config.sh`,
+`scripts/ai-video/lib/probe-audio.sh`, `scripts/media/lib/load-config.sh`,
 `scripts/ai-video/stitch.sh` — so a missing script fails here (with the
 path), not mid-run at Step 2/9.
 
@@ -155,7 +156,7 @@ if they really mean it; the guard never silently proceeds.
 
 ### 4. Load config + resolve providers
 
-Source `scripts/ai-video/lib/load-config.sh`. Resolve image / video
+Source `scripts/media/lib/load-config.sh`. Resolve image / video
 provider: command flag → `agents/.ai-video.xml` default → fail with the
 available-providers list. A **malformed XML** or a default/flag naming a
 provider with no `scripts/ai-video/adapters/<id>.sh` → fail fast here
@@ -487,4 +488,4 @@ labeled *modeled* (preview). No commit. No push.
 - [`/video:stitch`](stitch.md) — re-stitch after operator edits
 - [`song-to-script`](../../skills/song-to-script/SKILL.md) — audio →
   timed scene script
-- [`scripts/ai-video/lib/adapter-contract.md`](../../../scripts/ai-video/lib/adapter-contract.md)
+- [`scripts/media/lib/adapter-contract.md`](../../../scripts/media/lib/adapter-contract.md)

package/dist/agent-src/commands/video/scene.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-scene
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: scene
 description: Render a single scene from a one-line idea — scene-expander → blueprint → image → operator pick → motion → video. Preview mode default (no spend); --mode commit renders live behind the cost gate.
@@ -52,7 +53,7 @@ scripts/ai-video/lib/validate-deps.sh .agent-src.uncondensed/commands/video/scen
 
 ### 2. Load config + resolve providers
 
-Source `scripts/ai-video/lib/load-config.sh`. Resolve image / video
+Source `scripts/media/lib/load-config.sh`. Resolve image / video
 provider: flag → `agents/.ai-video.xml` default → fail with the
 available-providers list.
 

package/dist/agent-src/commands/video/stitch.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-stitch
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: stitch
 description: Re-stitch existing clips in `<project>/scenes/*/` after operator edits — no re-render. ffmpeg concat driven by manifest.json.

package/dist/agent-src/commands/video/storyboard.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-storyboard
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: storyboard
 description: Image-only storyboard — script → scenes → blueprint → image render → contact-sheet PNG via ffmpeg montage. No video calls.
@@ -41,7 +42,7 @@ scripts/ai-video/lib/validate-deps.sh .agent-src.uncondensed/commands/video/stor
 
 ### 2. Load config + resolve image provider
 
-Source `scripts/ai-video/lib/load-config.sh`. Resolve image provider:
+Source `scripts/media/lib/load-config.sh`. Resolve image provider:
 `--image-provider` flag → `agents/.ai-video.xml` default → fail. Reject
 `--video-provider` (this command produces no clips).
 

package/dist/agent-src/commands/video.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 description: Video-creation orchestrator — Hollywood-level AI video pipeline. Routes to from-script, from-song, scene, storyboard, stitch.
 type: orchestrator
@@ -23,7 +24,7 @@ video creation. Reads provider keys + defaults from
 [`agents/.ai-video.xml`](../../agents/templates/.ai-video.xml.example) (gitignored
 real file; example shipped). Every subcommand is **dry-run by default**;
 network calls require explicit per-turn confirmation per the adapter
-contract under [`scripts/ai-video/lib/adapter-contract.md`](../../scripts/ai-video/lib/adapter-contract.md).
+contract under [`scripts/media/lib/adapter-contract.md`](../../scripts/media/lib/adapter-contract.md).
 
 ## Sub-commands
 
@@ -70,5 +71,5 @@ contract under [`scripts/ai-video/lib/adapter-contract.md`](../../scripts/ai-vid
 
 ## See also
 
-- [`scripts/ai-video/lib/adapter-contract.md`](../../scripts/ai-video/lib/adapter-contract.md) — provider adapter v1 contract
-- [`docs/contracts/command-clusters.md`](../../docs/contracts/command-clusters.md) — `video` cluster registration
+- [`scripts/media/lib/adapter-contract.md`](../../scripts/media/lib/adapter-contract.md) — provider adapter v1 contract
+- [`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md) — `video` cluster registration

package/dist/agent-src/commands/work.md

@@ -6,6 +6,7 @@ intent: "Pick up the next sensible task and execute it autonomously"
 routes_to: [refine-prompt, command-routing]
 replaces: []
 tier: 0
+visibility: visible
 skills: [refine-prompt, command-routing]
 description: Drive a free-form prompt end-to-end through refine → score → plan → implement → test → verify → report — Option-A loop over the `work_engine` Python engine, confidence-band gated, no auto-git.
 suggestion:

package/dist/agent-src/contexts/augment-infrastructure.md

@@ -105,7 +105,7 @@ Commands organized by workflow:
 | **Modules** | `module-create`, `module-explore` |
 | **Roadmaps** | `roadmap:create`, `roadmap:process-step`, `roadmap:process-phase`, `roadmap:process-full` |
 | **Quality** | `quality-fix`, `review-changes`, `prepare-for-review`, `update-form-request-messages`, `fix-seeder` |
-| **CI/PR** | `fix-ci`, `create-pr`, `create-pr-description`, `fix-pr-comments`, `fix-pr-bot-comments`, `fix-pr-developer-comments` |
+| **CI/PR** | `fix-ci`, `create-pr`, `create-pr-description`, `fix-pr-comments` |
 | **Testing** | `tests-create`, `tests-execute` |
 | **E2E** | `e2e-plan`, `e2e-heal` |
 | **Agents** | `agents-prepare`, `agents-audit`, `agents-cleanup`, `copilot-agents-optimize`, `agent-handoff`, `agent-status`, `optimize-agents`, `optimize-augmentignore`, `optimize-skills`, `optimize-rtk-filters` |

package/dist/agent-src/contexts/communication/rules-auto/skill-quality-mechanics.md

@@ -25,7 +25,7 @@ Make descriptions "pushy" — explicit about when to fire:
   adjectives, drop the second example phrasing, or collapse a list — do
   **not** drop the trigger vocabulary or the `even if ...` tail.
 
-Source: [`skills/skill-creator` in `anthropics/skills`](https://github.com/anthropics/skills/blob/main/skills/skill-creator/SKILL.md).
+Source: [`skills/skill-creator` in `an external reference`](https://github.com/an external reference/blob/main/skills/skill-creator/SKILL.md).
 
 **Litmus test:** Read the description cold, without the skill's body. If you
 cannot name at least two phrasings a user would realistically type that should

package/dist/agent-src/contexts/communication/rules-auto/slash-command-routing-policy-mechanics.md

@@ -4,7 +4,7 @@ Lookup table for the `slash-command-routing-policy` rule. Lists the
 locked clusters and their sub-commands so the rule itself can stay at
 its current LOC while still reflecting the full surface. Source of
 truth for the cluster names is
-[`docs/contracts/command-clusters.md`](../../../../../docs/contracts/command-clusters.md);
+[`docs/contracts/command-clusters.md`](../../../../../../docs/contracts/command-clusters.md);
 this file mirrors that contract for runtime lookup. Linter:
 `scripts/check_cluster_patterns.py` (verifies dispatcher shape).
 
@@ -12,7 +12,7 @@ this file mirrors that contract for runtime lookup. Linter:
 
 | Cluster | Phase | Sub-commands | Replaces                                                                                                                                        |
 |---|:-:|---|-------------------------------------------------------------------------------------------------------------------------------------------------|
-| `/fix` | 1 | `ci` · `pr-comments` · `pr-bot-comments` · `pr-developer-comments` · `portability` · `refs` · `seeder` | `/fix-ci` · `/fix-pr-comments` · `/fix-pr-bot-comments` · `/fix-pr-developer-comments` · `/fix-portability` · `/fix-references` · `/fix-seeder` |
+| `/fix` | 1 | `ci` · `pr-comments` · `portability` · `refs` · `seeder` | `/fix-ci` · `/fix-pr-comments` · `/fix-portability` · `/fix-references` · `/fix-seeder` |
 | `/optimize` | 1 | `agents` · `augmentignore` · `rtk` · `skills` | `/optimize-agents` · `/optimize-augmentignore` · `/optimize-rtk-filters` · `/optimize-skills`                                                   |
 | `/feature` | 1 | `explore` · `plan` · `refactor` · `roadmap` | `/feature-explore` · `/feature-plan` · `/feature-refactor` · `/feature-roadmap`                                                                 |
 | `/chat-history` | 2 | `show` | `/chat-history` (legacy status) — `resume` / `clear` / `checkpoint` removed in `road-to-chat-history-hook-only`                                 |

package/dist/agent-src/contexts/communication/rules-auto/source-of-truth-mechanics.md

@@ -66,9 +66,9 @@ disable-model-invocation: true
 **Creating a new command:**
 
 1. Create `src/agent-src/commands/{name}.md` (use template)
-2. Run `python3 src/scripts/skill_linter.py` — must be 0 FAIL
+2. Run `./scripts-run src/scripts/skill_linter` — must be 0 FAIL
 3. Condense via `/condense`, which writes to `dist/agent-src/commands/`
-4. Run `python3 src/scripts/condense.py --generate-tools` — creates Claude symlink automatically
+4. Run `./scripts-run src/scripts/condense --generate-tools` — creates Claude symlink automatically
 
 **Never** create `.claude/skills/{name}/SKILL.md` manually for commands — always use the symlink workflow.
 
@@ -92,7 +92,7 @@ Commands have `disable-model-invocation: true` in their frontmatter.
 | Edit existing file | Edit in `src/`, condense to `dist/agent-src/` |
 | Create new `.md` | Create in `src/`, condense to `dist/agent-src/` |
 | Create new non-`.md` | Create in `src/`, run `bash src/scripts/condense.sh --sync` |
-| Create new command | Create in `src/agent-src/commands/`, sync, `python3 src/scripts/condense.py --generate-tools` |
+| Create new command | Create in `src/agent-src/commands/`, sync, `./scripts-run src/scripts/condense --generate-tools` |
 | Delete a file | Delete from `src/` and `dist/agent-src/` |
 | Check what needs condensation | `bash src/scripts/condense.sh --changed` |
 | Mark file as condensed | `bash src/scripts/condense.sh --mark-done {path}` |

package/dist/agent-src/contexts/communication/rules-auto/think-before-action-mechanics.md

@@ -42,12 +42,12 @@ behavior. Cannot → read more.
 
 ## Consult memory before editing
 
-Prior decisions and invariants live in the memory layer. Via
-[`memory-access`](../../../../../docs/guidelines/agent-infra/memory-access.md),
-call `retrieve(types=["architecture-decisions", "domain-invariants"], keys=<touched paths>, limit=3)`.
-A matching `architecture-decision` explains *why* the current shape
-exists; a matching `domain-invariant` is a hard constraint. Cite the
-`id` if a match influences the plan.
+Invariants live in the memory layer; architectural rationale lives in ADRs.
+Via [`memory-access`](../../../../../docs/guidelines/agent-infra/memory-access.md),
+call `retrieve(types=["domain-invariants"], keys=<touched paths>, limit=3)` —
+a matching `domain-invariant` is a hard constraint. For *why* the current
+shape exists, check the ADR index `docs/decisions/INDEX.md`. Cite the `id` /
+ADR number if a match influences the plan.
 
 ## Verify with real tools
 

package/dist/agent-src/contexts/communication/rules-auto/user-interaction-mechanics.md

@@ -82,7 +82,7 @@ position or framing:
    underneath.
 
 Mechanical backstop:
-`python3 scripts/check_reply_consistency.py --stdin < draft.md`
+`./scripts-run src/scripts/check_reply_consistency --stdin < draft.md`
 (non-zero exit on any rule above). Self-scan is the primary gate;
 the script is the deterministic safety net for ambiguous cases.
 

package/dist/agent-src/contexts/contracts/consumer-agents-md-guide.md

@@ -38,10 +38,10 @@ covers). Default: leave AGENTS.md thin and put detail under `agents/`.
 ```markdown
 ## Development Setup
 
-​```bash
+```bash
 {{dev_start_command}}    # make start / docker compose up / npm run dev / php artisan serve
 {{dev_test_command}}     # make test / docker compose exec app bash / npm test / php artisan test
-​```
+```
 
 ### Environment files
 

package/dist/agent-src/contexts/execution/evidence-discipline.md

@@ -0,0 +1,153 @@
+# Evidence Discipline — Report format, provenance, enforcement reality
+
+Canonical definitional spine for evidence-first structure discipline. Loaded by
+[`source-discovery`](../../rules/source-discovery-gate.md) rule and skill. Skill
+holds the *procedure*; this file holds the *definitions* every later phase, the
+linter, and ADRs refer back to.
+
+## The invariant
+
+```
+NO STRUCTURAL CLAIM WITHOUT EVIDENCE FROM A REAL SOURCE.
+EVERY FIELD, ENDPOINT, COLUMN, AND VALUE TRACES TO file:line · SDL · migration · probe.
+LOCAL BEFORE REMOTE. REAL SOURCE BEFORE GUESSING.
+```
+
+Product is a **discipline**, not a knowledge database. A card is only an optional
+cache for *expensive* evidence — never a source of truth, never a build input.
+
+## Evidence Report — discovery output
+
+Gitignored session scratchpad (`agents/memory/knowledge/session/`, overwritten each
+task), produced **before** the plan, soft-capped to ~10–20 decision-relevant facts.
+Three buckets:
+
+- **Verified** — confirmed **this session** against a real source, **or** durable
+  committed-card content (negative facts + pointers, pointer-CI green). Nothing else qualifies.
+- **Assumed (from card)** — positive structural claims from a committed card but
+  **not** confirmed this session; explicitly a hypothesis. A card's positive structure
+  is **never** "Verified", even with a green pointer (R4 P1).
+- **Gaps** — missing evidence the decision needs (negative facts in the making).
+
+Feeds the plan. Not a forensic log, not hard enforcement. Produce cheaply via
+`evidence_report.py` so it never gets skipped.
+
+## Provenance and freshness
+
+- Every item carries `observed_at`, `source`, `version` where one exists. Card
+  **positive-structure lines** carry **per-line** `observed_at` / `source_version` (R4 P5).
+- **Within a session:** read is fresh until file's **mtime** changes.
+- **Invalidate all session reads when `git rev-parse HEAD` changes** — new HEAD means
+  tree may have moved.
+- **Fail-fast mid git-op:** if rebase/merge/cherry-pick is in progress
+  (`.git/MERGE_HEAD`, `.git/CHERRY_PICK_HEAD`, or `.git/rebase-merge`/`rebase-apply`
+  present), do **not** read an intermediate tree — stop and surface it (R4 P6,
+  hole-3). *(`.git/REBASE_HEAD` excluded — lingers as stale ref after completed
+  rebase, not a live-op marker.)* `evidence_report.py git-state` is the
+  deterministic check.
+- **Across sessions:** always re-read. No file hashing, no content-hash theater.
+
+## Two-file split
+
+| File | Home | Tracked? | Holds |
+|---|---|---|---|
+| **Ephemeral session cache** | `agents/memory/knowledge/session/` | gitignored | Evidence Report + raw probe/introspection dumps + absence-search log |
+| **Committed card** | `agents/knowledge/<source>.md` | tracked | thin distillation: `trust: durable` negative facts + pointers; positive structure as per-line last-verified hypothesis |
+
+Committed card extends `context-document` mechanism (a specialized context type)
+— **not** a second knowledge system.
+
+## DB-not-in-codebase boundary (R4 P2)
+
+- **In-codebase** = schema defined by repo migrations / models / ORM / app code —
+  **including** schemaless stores the app controls (Mongoose, Prisma, Firestore
+  rules). → always **local, read fresh, no card**.
+- **DB-not-in-codebase** = no repo migrations/models/app-code define the schema
+  **and** app does not control it (vendor SaaS, partner, legacy DB). → may be
+  **card-worthy** (remote evidence).
+
+## Negative facts (R4 P4)
+
+A negative fact is a **current-state fact** — "searched X, did not find Y" — not a
+card-worthiness *decision* (belongs in notes/ADR, never an anti-hallucination card).
+Write a negative-fact card **only after search is exhausted across all relevant
+sources**, logging `searched` *and* `not_searched`, attach a `revalidate_if` trigger.
+
+## Card-worthiness threshold (R3 F-3, R4 P2/P7)
+
+Card-worthy = **(external package / remote API / DB-not-in-codebase)** AND **(≥3
+distinct methods/fields *intended* to be used OR source exposes >50 methods and ≥1
+is used OR prior hallucination OR local types/README insufficient)**. Judged on
+**intended** use at discovery. Cross-feature duplication check flags structure
+discovered in >1 session without a card as "should-have-been-card-worthy".
+
+## L0–L4 — descriptive, not prescriptive
+
+L0–L4 are human shorthand for discovery depth; documentation only. **Same** evidence
+rules apply at every tier — no enforced state machine, no per-tier relaxation.
+
+## Honest enforcement reality
+
+```
+THE SELF-LOG IS INSTRUMENTATION, NOT ENFORCEMENT.
+A MODEL THAT INVENTS A FIELD CAN ALSO WRITE A FALSE "VERIFIED".
+THE TEETH ARE POINTER-CI (DETERMINISTIC) + THE ANTI-HALLUCINATION EVAL (EMPIRICAL).
+```
+
+- **Instrumentation (soft):** Evidence Report and any `card_claims` self-log. Useful
+  signal; never oversold as a guarantee.
+- **Teeth (hard):** pointer-resolution CI (path exists / URL 200, strict-mode
+  content-compare) + multi-evidence git-ancestry consistency check +
+  per-surface anti-hallucination eval with variance baseline.
+
+## Global layer (v2 — cross-project card sharing, ADR-100)
+
+An *expensive* (remote) card may be promoted from project-local `agents/knowledge/`
+to per-user **file-first** global store at `~/.event4u/agent-config/knowledge/`
+(no daemon / DB / vector index / decay — 2026-06-14 Layer-2 sunset's core preserved).
+**Storage, not governed** like a committed card: unversioned, a cache, never a source
+of truth. Gated by `knowledge.global_sharing` setting (**default OFF until
+cross-project reuse is measured across ≥ 2 real projects** — ADR-103 amends ADR-100
+Phase 0; `enabled: false` fully no-ops the layer — v1 unaffected; operator opts in
+explicitly; default flips back only on positive reuse signal).
+
+- **Global card is a distillation, not a copy.** `trust: durable` core is
+  **negative facts + pointers**; positive structure is explicit per-line
+  **hypothesis** — never copied as build input.
+- **Leads-only consumption.** Global card enters Evidence Report as **"Assumed (from
+  card · GLOBAL, unverified)"** — positive structure must be re-confirmed against
+  live source *this session*. Negative facts + pointers are usable as leads.
+  Global-sourced positive structure is **never** "Verified".
+- **Origin-tier scoping is the privacy floor.** `public` auto-shareable; `vendor`
+  shareable **post-redaction**; `proprietary` **manual-only, default-off regardless
+  of `enabled`** — no client-A schema leaks into client-B.
+- **Redaction on write.** Promotion runs the `low-impact-corpus-privacy-floor` +
+  `source-confidentiality` pattern set and **halts** on any hit — never
+  silent-shares, never auto-rewrites.
+- **Promotion is hybrid.** Card seen in ≥`auto_promote_threshold` distinct repos
+  triggers a one-tap **suggestion**; never a silent write.
+
+## Evidence v2 rollback target (Phase 0)
+
+Evidence v2 (self-building project context — Class A config-pointers, Class B
+observed conventions, Class C learned lessons) is an **additive** layer. Rollback
+target is fixed and measurable:
+
+```
+v2 ROLLBACK = DISABLE ALL CURATED ACCUMULATED CONTEXT EXCEPT CLASS-A CONFIG-POINTERS.
+THE MEASURABLE BASELINE TO REVERT TO IS v1 DISCIPLINE WITH NO ACCUMULATED CONTEXT.
+```
+
+Class A (config-derived pointers) is deterministic, drift-proof, no accumulation
+risk → survives rollback. Class B/C are accumulation layers; if v2 eval shows
+accumulated context raises error rate or cost is disproportionate, those layers are
+disabled and agent runs v1 alone — acceptable outcome. "Self-improving" is a
+hypothesis, not a law; rollback target makes the hypothesis falsifiable.
+
+## See also
+
+- [`project-intelligence`](project-intelligence.md) — Evidence v2: self-building context (A/B/C classes, memory tiers, the v1↔v2 isolation contract).
+- [`source-discovery`](../../rules/source-discovery-gate.md) — the obligation surface.
+- [`source-discovery`](../../skills/source-discovery/SKILL.md) — the procedure.
+- [`think-before-action`](../../rules/think-before-action.md) — minimum read set + verification matrix.
+- [`context-document`](../../skills/context-document/SKILL.md) — the card's parent mechanism.