@event4u/agent-config 6.0.0 → 6.1.0

package/dist/agent-src/skills/feature-planning/SKILL.md

@@ -167,7 +167,7 @@ complexity: lightweight  # default — skips bite-sized granularity
 ---
 ```
 
-Source: adapted from `obra/superpowers` `writing-plans/SKILL.md` § Task Structure + § No Placeholders (v5.1.0); complexity-gating is our addition (Council Round 1, Q4 — mitigates UX pushback for senior engineers on well-scoped work).
+Source: adapted from an external reference `writing-plans/SKILL.md` § Task Structure + § No Placeholders (v5.1.0); complexity-gating is our addition (Council Round 1, Q4 — mitigates UX pushback for senior engineers on well-scoped work).
 
 ## Self-review (3-scan checklist)
 
@@ -179,7 +179,7 @@ Before presenting any plan, run these three scans in order. Each is a fast pass
 
 This scan is **separate from** adversarial-review (below). Self-review catches mechanical gaps (missing AC, leftover placeholders, mis-shaped types); adversarial-review challenges the plan's reasoning.
 
-Source: adapted from `obra/superpowers` `writing-plans/SKILL.md` § Self-Review (v5.1.0).
+Source: adapted from an external reference `writing-plans/SKILL.md` § Self-Review (v5.1.0).
 
 ## Adversarial self-review
 

package/dist/agent-src/skills/mcp-builder/SKILL.md

@@ -107,7 +107,7 @@ Process: enumerate the tools, explore READ-ONLY data, draft 10 questions, **solv
 
 - Upstream protocol: https://modelcontextprotocol.io
 - Upstream SDKs: https://github.com/modelcontextprotocol/python-sdk · https://github.com/modelcontextprotocol/typescript-sdk
-- Adopted from: `Microck/ordinary-claude-skills@8f5c83174f7aa683b4ddc7433150471983b93131:skills_all/mcp-builder/SKILL.md` (MIT, © 2025 Microck) — external `./reference/*.md` file links replaced with inline guidance + upstream URLs.
+- Adopted from: an external reference (MIT, © 2025 an external reference) — external `./reference/*.md` file links replaced with inline guidance + upstream URLs.
 - Cross-linked: [`mcp`](../mcp/SKILL.md), [`testing-anti-patterns`](../testing-anti-patterns/SKILL.md), [`api-design`](../api-design/SKILL.md).
 - Provenance registry: `agents/settings/contexts/skills-provenance.yml` (entry: `mcp-builder`).
 - Iron-Law floor: `verify-before-complete`, `tool-safety`, `skill-quality`.

package/dist/agent-src/skills/memory-consolidation/SKILL.md

@@ -90,13 +90,15 @@ miner is too loose; tighten patterns and re-run before promoting.
 
    A fact may carry **two** tags; the promoter resolves via tag
    intersection, not by file extension. See
-   [`docs/contracts/agent-memory-contract.md`](../../../docs/contracts/agent-memory-contract.md)
-   for the curated YAML schemas.
+   [`memory-access`](../../../docs/guidelines/agent-infra/memory-access.md)
+   for the file-backed retrieval contract over the curated YAML.
 
 2. Append each fact as one JSONL line to
    `agents/memory/intake/<primary-tag>.jsonl` with required fields
    per the contract: `ts`, `type`, `key`, `observation`, `source:
    agent`, `session_id`, plus the new optional `tags: [<one>, <two>]`.
+   Intake is **gitignored, local scratch** — only entries promoted to
+   curated YAML (next phase) become team-shared (committed).
 3. Default to `--preview` mode: render the JSONL block to stdout and
    stop. Only `--commit-intake` writes the file.
 
@@ -109,13 +111,45 @@ validates against the contract.
    archive the consumed JSONL lines into
    `agents/memory/intake/.archive/YYYY-Www.jsonl` — week-bucketed,
    not day-bucketed (defeats session-context inference attacks).
-2. If a curated entry's `last_validated` field is older than 90 days
-   AND no signal in the last 30 days touched its `key`, mark it
-   stale in the consolidation report — but do **not** auto-delete.
-   Pruning is a human-confirmed action.
-
-**Exit gate:** report cites ≥ 0 promotions, ≥ 0 stale flags, 0
-auto-deletes.
+2. **Delete `status: archived` curated entries.** Once an entry is
+   marked `archived` (by review or supersession), remove it from the hot
+   file — **git history is the cold archive** (`git log -- <file>`
+   recovers it). This keeps the committed memory small without a decay
+   engine. Do not keep an `agents/memory/archive/` directory.
+3. If an *active* curated entry's `last_validated` is older than 90 days
+   AND no signal in the last 30 days touched its `key`, mark it stale in
+   the consolidation report — but do **not** auto-delete a still-active
+   entry. Only `archived` entries are deleted; staleness is a flag, not a
+   delete trigger.
+
+**Exit gate:** report cites ≥ 0 promotions, ≥ 0 stale flags, and the
+count of `archived` entries deleted (git history retains them).
+
+## Write-time curation discipline
+
+Memory quality comes from what you write, not from a heavy store. Apply
+these at GATHER + CONSOLIDATE (adapted from MemSkill's memory-operation
+skills — github.com/ViktorAxelsen/MemSkill, Apache-2.0, commit `9907c35f8cc7`):
+
+- **Dedupe before insert.** Compare against retrieved entries; never add a
+  fact already covered. Split distinct facts into separate entries.
+- **Merge on refresh, preserve what still holds.** When a fact updates an
+  existing entry, merge into one item and keep the details that remain true.
+- **Delete only on explicit contradiction.** Remove a curated entry only when
+  evidence directly contradicts or cancels it. If uncertain, keep it.
+- **Prefer no-op under uncertainty.** A chunk with no new, corrective, or
+  actionable information records nothing — silence beats speculation.
+- **Skip trivial / fleeting / speculative content.** Capture durable,
+  reusable facts, not transcripts or one-off chatter.
+- **One durable fact per entry.** No narrative blobs — each entry is a single
+  PATTERN / CONVENTION / INVARIANT / GOTCHA the next agent can act on.
+
+This is **meta-memory**: the skill of *how to remember* (what to extract,
+keep, forget) — distinct from the remembered content. The store stays simple
+and file-backed; the discipline lives here. Do **not** add
+INSERT/UPDATE/DELETE/NOOP operation machinery (append-only JSONL + curated
+YAML need no such ops) and do **not** import any retrieval / decay / trust
+engine.
 
 ## TranscriptAdapter contract
 
@@ -134,11 +168,24 @@ The miner is host-agnostic by design. A `TranscriptAdapter` for host
   identifier the consumer project lists in
   `.agent-settings.yml` under `memory.redact_patterns`.
 
-Phase 1 implementation lives in
-`/memory:mine-session` (single host: Claude Code,
-`~/.claude/projects/*/sessions/*.jsonl`). Phase 3 of the
-adoption roadmap adds a second host adapter; the contract above is
-documented now so the second implementation is not a vacuum design.
+The GATHER implementation lives in the single mining command
+`/memory:mine-session` (`scripts/mine_session.py`). It reads the
+**cross-host** chat-history JSONL log (`agents/runtime/.agent-chat-history`,
+written by platform hooks on every host), falling back to the per-host
+Claude-Code transcript when the log is absent. `--mode=[signals|proposals|both]`
+selects intake signals and/or rule/skill proposal seeds — the latter folds in
+the former `/chat-history learn`.
+
+## In-task notes → cross-run lessons (RDP)
+
+The Reasoning Discipline Protocol writes an **in-task** session-notes file
+(hypotheses, killed beliefs, predictions, decisions, uncertainty — structure in
+[`notes-first-reasoning`](../../rules/notes-first-reasoning.md)). That file is
+ephemeral working state, not curated memory. This skill is the **promotion path**:
+when an in-task killed-belief, calibrated prediction, or decision *generalises*
+beyond the task, consolidate it here as a durable cross-run lesson (one lesson per
+file, with why it mattered). Apply the same signal-vs-noise discipline — most
+in-task notes stay in-task and are discarded with the task.
 
 ## Related Skills
 
@@ -196,9 +243,8 @@ documented now so the second implementation is not a vacuum design.
 
 - Do NOT auto-trigger this skill on session end. The flow is manual,
   per-invocation, and confirmed.
-- Do NOT vendor patterns or text from `grandamenium/dream-skill` —
-  the upstream lacks a `LICENSE`. Concept and procedure structure are
-  the only adoption surface.
+- Do NOT vendor patterns or text from any external source. Concept and
+  procedure structure are the only adoption surface.
 - Do NOT promote a normalised fact whose `key` falls outside the
   repo root or names another consumer project.
 - Do NOT delete a stale curated entry without explicit user

package/dist/agent-src/skills/prompt-engineering-patterns/SKILL.md

@@ -144,7 +144,7 @@ Production prompts handle their own failure cases:
 
 ## Provenance
 
-- Adopted from: `Microck/ordinary-claude-skills@8f5c83174f7aa683b4ddc7433150471983b93131:skills_all/prompt-engineering-patterns/SKILL.md` (MIT, © 2025 Microck) — restructured into a decision-framework shape; vendor `prompt_optimizer` Python snippets dropped (project-specific to Microck).
+- Adopted from: an external reference (MIT, © 2025 an external reference) — restructured into a decision-framework shape; vendor `prompt_optimizer` Python snippets dropped (project-specific to an external reference).
 - Cross-linked: [`prompt-optimizer`](../prompt-optimizer/SKILL.md), [`refine-prompt`](../refine-prompt/SKILL.md), [`mcp-builder`](../mcp-builder/SKILL.md), [`async-python-patterns`](../async-python-patterns/SKILL.md).
 - Provenance registry: `agents/settings/contexts/skills-provenance.yml` (entry: `prompt-engineering-patterns`).
 - Iron-Law floor: `verify-before-complete`, `skill-quality`, `non-destructive-by-default`.

package/dist/agent-src/skills/readme-writing-package/SKILL.md

@@ -263,7 +263,7 @@ Pair the catalog with a separate "Global install" subsection (same flags
 plus `--global`) and an "Other commands" subsection. Reference example:
 [`README.md § Pick specific AIs`](../../../README.md#pick-specific-ais) in
 this repository. Inspiration:
-[`ui-ux-pro-max-skill § Installation`](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill#installation).
+[`an external reference suite § Installation`](https://github.com/an external reference suite#installation).
 
 Use the catalog when the package's primary install action varies by
 platform; use a matrix table (Tool / Rules / Skills / Commands) for

package/dist/agent-src/skills/reasoning-orchestrator/SKILL.md

@@ -0,0 +1,119 @@
+---
+name: reasoning-orchestrator
+description: "Use for complex / ambiguous / long-horizon work — coordinate the reasoning chain ground→intent→notes→gather→audit→verify; composes existing skills, never duplicates them."
+source: package
+domain: engineering
+status: active
+model_tier: medium
+tier: senior
+context_spine: [repo]
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+requires_skills:
+  - memory-consolidation
+  - adversarial-review
+  - subagent-orchestration
+  - complexity-first-planning
+---
+
+# reasoning-orchestrator
+
+The **primary coordination mechanism** of the Reasoning Discipline Protocol
+(roadmap L6). It is behavioral glue — like [`subagent-orchestration`](../subagent-orchestration/SKILL.md)
+and [`feature-planning`](../feature-planning/SKILL.md) — that sequences the
+discipline so it acts as one system instead of a buffet of optional steps. It
+**composes** the underlying skills/rules; it never re-implements them, and it
+adds **no new flow** (it is invoked within discovery/implementation, honoring
+`src/flows/README.md`).
+
+Engage per [`rdp-gate`](../../contexts/execution/rdp-gate.md): skip on trivial
+tasks; on a strong-reasoning host run **light / as suggestion** (it self-
+coordinates); on a standard host run the full chain.
+
+## When to use
+
+- A complex, ambiguous, or long-horizon task on a standard host.
+- Work where the reasoning steps are interdependent (a missed grounding or skipped
+  verification compounds downstream).
+
+Do NOT use for trivial / linear / fully-specified tasks (the gate filters these),
+and do not let it duplicate the work of the skills it coordinates.
+
+## When the agent should load this
+
+- A task is complex / ambiguous / long-horizon and the host is a standard model.
+- The reasoning steps are interdependent and a skipped link (grounding,
+  verification) would compound downstream.
+- Several discipline skills would otherwise fire piecemeal — load this to make
+  them act as one ordered chain instead of a buffet of optional steps.
+
+## Procedure — the chain it enforces
+
+Each link **delegates** to the artifact that owns it (no duplication):
+
+1. **ground** — close constraints/tools/info-gaps before designing
+   ([`think-before-action` § Environment grounding](../../rules/think-before-action.md)).
+2. **intent** — state the inferred goal + one recommendation, standard host only
+   ([`improve-before-implement` § Intent inference](../../rules/improve-before-implement.md)).
+3. **notes** — hypotheses/predictions/decisions/uncertainty to the notes file, not
+   the response ([`notes-first-reasoning`](../../rules/notes-first-reasoning.md)).
+4. **gather** — resolve the load-bearing unknown first
+   ([`complexity-first-planning`](../complexity-first-planning/SKILL.md)); dispatch
+   independent subtasks async ([`subagent-orchestration` § RDP](../subagent-orchestration/SKILL.md)).
+5. **audit** — check progress against real tool results
+   ([`verify-before-complete`](../../rules/verify-before-complete.md)).
+6. **verify** — fresh-context verifier on the structural-complexity gate
+   ([`adversarial-review` § RDP](../adversarial-review/SKILL.md)).
+
+## Fail-safe
+
+If the orchestrator does not fire (gate off, or the host skips it), the
+individual skills/rules still apply on their own triggers — the discipline
+degrades gracefully to the distributed extensions rather than disappearing. The
+orchestrator's value is **coherence** (the links happen in order, with handoffs),
+not exclusivity.
+
+## Output
+
+The task's actual deliverable — produced through the chain. Reasoning stays in the
+notes file; the response leads with the outcome + its evidence.
+
+## Do NOT
+
+- Re-implement grounding / verification / planning here — **delegate**.
+- Create a new flow or a standalone pack — this is a skill invoked within existing flows.
+- Run the full chain on a strong-reasoning host or a trivial task — the gate says light/off.
+
+## Gotchas
+
+- **Buffet collapse.** Without the orchestrator, the discipline skills fire
+  independently and the chain's *order* is lost (verification before grounding,
+  notes never written). The whole value is the ordered handoff — running the
+  links out of sequence is the failure this skill prevents.
+- **Duplication creep.** Inlining a delegated step's logic here (re-doing the
+  grounding instead of pointing at `think-before-action`) silently forks the
+  behavior; the two copies then drift. Always delegate, never re-implement.
+- **Wrong host, full chain.** Running every link on a strong-reasoning host wastes
+  tokens and reads as nagging — the gate says light/suggestion there. Forcing the
+  full chain regardless of host is a cost regression, not rigor.
+
+## Related Skills
+
+**WHEN to use this**
+
+- A complex / ambiguous / long-horizon task on a standard host where the reasoning
+  links are interdependent.
+- Several discipline skills would otherwise fire piecemeal and need ordering.
+
+**WHEN NOT to use this**
+
+- Trivial / linear / fully-specified tasks — the
+  [`rdp-gate`](../../contexts/execution/rdp-gate.md) filters these.
+- A single discipline step in isolation — invoke that skill/rule directly
+  ([`think-before-action`](../../rules/think-before-action.md),
+  [`verify-before-complete`](../../rules/verify-before-complete.md)) instead of the
+  whole chain.
+- Needing the rationale behind the protocol — read
+  [`frontier-reasoning-operating-profile`](../../../../docs/guidelines/agent-infra/frontier-reasoning-operating-profile.md).

package/dist/agent-src/skills/reasoning-orchestrator/evals/triggers.json

@@ -0,0 +1,16 @@
+{
+  "skill": "reasoning-orchestrator",
+  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers complex / ambiguous / long-horizon work on a standard host where the reasoning steps are interdependent; should-not covers trivial / linear tasks, strong-host self-coordination, and single-discipline neighbors.",
+  "queries": [
+    {"q": "refactor the entire billing module to be cleaner and safer", "trigger": true},
+    {"q": "build this feature end to end from a vague brief — figure out the steps", "trigger": true},
+    {"q": "investigate this flaky multi-service failure and fix it properly", "trigger": true},
+    {"q": "take this ambiguous ticket and drive it to a verified implementation", "trigger": true},
+    {"q": "plan and implement the migration with checks at each stage", "trigger": true},
+    {"q": "rename this variable", "trigger": false, "note": "trivial — gate off"},
+    {"q": "format this file", "trigger": false, "note": "trivial"},
+    {"q": "just write the regex for an email", "trigger": false, "note": "single linear step"},
+    {"q": "only run the test suite and report", "trigger": false, "note": "single-discipline (verify), no chain to coordinate"},
+    {"q": "add a one-line log statement here", "trigger": false, "note": "trivial"}
+  ]
+}

package/dist/agent-src/skills/receiving-code-review/SKILL.md

@@ -84,11 +84,12 @@ For each comment classified as blocking/important:
   for a reason
 * **Consult memory for prior context.** Via
   [`memory-access`](../../../docs/guidelines/agent-infra/memory-access.md),
-  call `retrieve(types=["historical-patterns", "architecture-decisions"],
+  call `retrieve(types=["historical-patterns"],
   keys=<files in the review>, limit=3)`. A registered historical pattern
-  may confirm the reviewer's concern (accept) or an architecture
-  decision may explain why the current shape is intentional (push back
-  with the cited `id`).
+  may confirm the reviewer's concern (accept). For architectural rationale
+  ("why is the current shape intentional?"), check the ADR index
+  [`docs/decisions/INDEX.md`](../../../docs/decisions/INDEX.md) — push back
+  with the cited ADR number.
 
 ### 4. Decide: accept, push back, or escalate
 
@@ -178,8 +179,7 @@ When reporting back to the user after handling review:
 ## When to hand over to another skill / command
 
 * Executing the fixes across many comments → [`fix-pr-comments`](../../commands/fix-pr-comments.md)
-  (handles both bot + developer), [`fix-pr-bot-comments`](../../commands/fix-pr-bot-comments.md),
-  [`fix-pr-developer-comments`](../../commands/fix-pr-developer-comments.md)
+  (handles both bot + human reviewers in one pass)
 * Running the full verification gate before pushing replies →
   [`verify-before-complete`](../verify-before-complete/SKILL.md)
 * Writing the commit message that references the review →

package/dist/agent-src/skills/refine-prompt/SKILL.md

@@ -183,7 +183,7 @@ Before emitting the envelope, run these three scans. Each is a fast pass; failur
 2. **Placeholder / TODO scan** — the rendered envelope contains no `<placeholder>`, `TODO`, `FIXME`, `tbd`, `???`, `XXX` strings. The literal angle-bracket placeholders in the template (`<one sentence …>`, `<bullet>`) must be replaced with concrete text before emission.
 3. **Type / shape consistency** — every named file, module, route, or command in the AC matches the project's existing conventions. If the prompt names `auth.service.ts` but the codebase uses `AuthService.php`, surface the mismatch in *Assumptions* rather than adopting the prompt's spelling.
 
-Source: adapted from `obra/superpowers` `writing-plans/SKILL.md` § Self-Review (v5.1.0).
+Source: adapted from an external reference `writing-plans/SKILL.md` § Self-Review (v5.1.0).
 
 ## Band-action mapping
 

package/dist/agent-src/skills/refine-ticket/SKILL.md

@@ -272,7 +272,7 @@ Run these three scans on the rendered output before the close-prompt. Each is a
 
 Self-review is mechanical (gaps, leftovers, naming drift); persona voices and orchestration outputs handle reasoning critique. Both run; neither replaces the other.
 
-Source: adapted from `obra/superpowers` `writing-plans/SKILL.md` § Self-Review (v5.1.0).
+Source: adapted from an external reference `writing-plans/SKILL.md` § Self-Review (v5.1.0).
 
 ## Close-prompt (mandatory final step)
 

package/dist/agent-src/skills/repomix-packer/SKILL.md

@@ -136,6 +136,6 @@ Cite the snapshot path so the consumer skill can read it.
 ## Provenance
 
 - Upstream tool: https://github.com/yamadashy/repomix (MIT).
-- Adopted from: `Microck/ordinary-claude-skills@8f5c83174f7aa683b4ddc7433150471983b93131:skills_all/repomix/SKILL.md` (MIT, © 2025 Microck) — wrapper-style adoption, no upstream code vendored.
+- Adopted from: an external reference (MIT, © 2025 an external reference) — wrapper-style adoption, no upstream code vendored.
 - Provenance registry: `agents/settings/contexts/skills-provenance.yml` (entry: `repomix`).
 - Iron-Law floor: `non-destructive-by-default`, `missing-tool-handling`, `tool-safety`.

package/dist/agent-src/skills/secrets-management/SKILL.md

@@ -135,7 +135,7 @@ Telemetry / APM     → strip from request/response captures; allowlist headers.
 
 ## Provenance
 
-- Adopted from: `Microck/ordinary-claude-skills@8f5c83174f7aa683b4ddc7433150471983b93131:skills_all/secrets-management/SKILL.md` (MIT, © 2025 Microck) — **Sunset Policy applied**: 346-line provider cookbook reduced to a ~140-line decision framework; per-provider deep-dives externalized to upstream docs below.
+- Adopted from: an external reference (MIT, © 2025 an external reference) — **Sunset Policy applied**: 346-line provider cookbook reduced to a ~140-line decision framework; per-provider deep-dives externalized to upstream docs below.
 - Externalized provider docs:
   - HashiCorp Vault: https://developer.hashicorp.com/vault/docs · https://developer.hashicorp.com/vault/docs/secrets/databases
   - AWS Secrets Manager: https://docs.aws.amazon.com/secretsmanager/ · rotation: https://docs.aws.amazon.com/secretsmanager/latest/userguide/rotating-secrets.html

package/dist/agent-src/skills/subagent-orchestration/SKILL.md

@@ -49,6 +49,13 @@ judge is a fresh pair of eyes. If `.agent-settings.yml` resolves to
 identical implementer and judge models, surface the mismatch before
 running — do not silently continue.
 
+## RDP: parallel async dispatch by default
+
+Within the Reasoning Discipline Protocol, dispatch independent subtasks to
+parallel subagents **by default** and keep working while they run (async), rather
+than blocking on each return — intervene only if one goes off track. Engage per
+[`rdp-gate`](../../contexts/execution/rdp-gate.md).
+
 ## The seven modes
 
 Each mode has a decision row: when to use, when not, and the expected
@@ -60,8 +67,8 @@ model pairing. Defaults come from
 Descriptive, not enforced. Documents the **expected agent-to-agent
 communication topology** so consumers can predict latency, failure
 modes, and where consensus is required. Cited from
-[`external-findings.md § 2`](../../../agents/runtime/council/sessions/audit-2026-05-14-north-star/external-findings.md) <!-- council-ref-allowed: ADR decision trace for topology anti-drift defaults -->
-row 7 (Ruflo's `hierarchical, 6–8 agents, raft consensus` anti-drift
+an internal findings note (local-only) <!-- council-ref-allowed: ADR decision trace for topology anti-drift defaults -->
+row 7 (the external runtime's `hierarchical, 6–8 agents, raft consensus` anti-drift
 default).
 
 | Mode | Topology | Anti-drift default | Notes |
@@ -74,7 +81,7 @@ default).
 | judge-with-debate | `hierarchical-mesh` | 2 judges · 1 meta-judge | Judges debate (mesh edge); meta-judge reconciles (hierarchical). |
 | do-in-worktrees | `adaptive` | per-step topology of the underlying mode | Each worktree picks its own shape; chain is hierarchical. |
 
-**Anti-drift default** (Ruflo convention, descriptive only):
+**Anti-drift default** (the external runtime convention, descriptive only):
 `hierarchical, 6–8 agents, raft consensus`. Consumers free to
 override per orchestration — the table is the **starting point**,
 not a constraint. Topology is metadata for capacity planning, not

package/dist/agent-src/skills/testing-anti-patterns/SKILL.md

@@ -158,7 +158,7 @@ Gate: a feature is not complete until a failing-then-passing test cycle ran for
 
 ## Provenance
 
-- Adopted from: `Microck/ordinary-claude-skills@8f5c83174f7aa683b4ddc7433150471983b93131:skills_all/testing-anti-patterns/SKILL.md` (MIT, © 2025 Microck).
+- Adopted from: an external reference (MIT, © 2025 an external reference).
 - Cross-linked: [`pest-testing`](../pest-testing/SKILL.md), [`test-driven-development`](../test-driven-development/SKILL.md), [`judge-test-coverage`](../judge-test-coverage/SKILL.md).
 - Provenance registry: `agents/settings/contexts/skills-provenance.yml` (entry: `testing-anti-patterns`).
 - Iron-Law floor: `verify-before-complete`, `skill-quality`.

package/dist/agent-src/skills/testing-anti-patterns/process-anti-patterns.md

@@ -61,7 +61,7 @@ the rationalization, then reject it:
 
 ## Provenance
 
-- Adapted from `obra/superpowers@v5.1.0` `testing/anti-patterns.md`.
+- Adapted from an external reference `testing/anti-patterns.md`.
 - Council convergence (anthropic/claude-sonnet-4-5 + openai/gpt-4o,
   2026-05-07): both members ADOPT — the catalogue surfaces specific
   rationalization patterns that would otherwise leak past code review.

package/dist/agent-src/skills/token-optimizer/SKILL.md

@@ -80,7 +80,7 @@ INTENT
 | `agent-handoff` | `.claude/skills/agent-handoff/SKILL.md` | `handoff`, `fresh`, `chat`, `context` | Context envelope for fresh-chat continuation |
 | `direct-answers` | `.agent-src.uncondensed/rules/direct-answers.md` | `brevity`, `flattery`, `severity`, `tiered` | Iron-Law brevity floor (kernel) |
 | `markitdown` | upstream: github.com/microsoft/markitdown | `PDF`, `DOCX`, `HTML`, `convert` | Document → markdown converter (authoritative-link only) |
-| `/cost:report` | TBD — `road-to-ruflo-adoption.md § P1.2` | `cost`, `model spend`, `budget` | Per-session cost telemetry (planned) |
+| `/cost:report` | TBD — an internal roadmap (local-only) | `cost`, `model spend`, `budget` | Per-session cost telemetry (planned) |
 
 ## Output format
 

package/dist/agent-src/templates/agents/.gitattributes.fragment

@@ -11,6 +11,5 @@ agents/memory/intake/*.jsonl merge=union eol=lf
 agents/memory/ownership/*.yml              text eol=lf
 agents/memory/historical-patterns/*.yml    text eol=lf
 agents/memory/domain-invariants/*.yml      text eol=lf
-agents/memory/architecture-decisions/*.yml text eol=lf
 agents/memory/incident-learnings/*.yml     text eol=lf
 agents/memory/product-rules/*.yml          text eol=lf

package/dist/agent-src/templates/agents/agent-project-settings.example.yml

@@ -116,9 +116,9 @@ modules:
 
 # --- Memory layer (optional) ---
 #
-# Opt-in signal for the @event4u/agent-memory companion package and
-# the repo-shared curated-memory files. If omitted, memory features
-# stay inert — no writes, no reads, no nagging.
+# Opt-in signal for the repo-shared, file-backed curated-memory files
+# under `agents/memory/`. If omitted, memory features stay inert —
+# no writes, no reads, no nagging.
 memory:
   # Enable curated memory files under `agents/memory/` as part of
   # this repo's dogfooding of its own memory conventions. Only flip
@@ -278,7 +278,7 @@ locked_keys: []
 # files live here when memory.dogfood is true. These paths are for
 # reference only — no enforcement is done from this file.
 references:
-  architecture_decisions: agents/memory/architecture-decisions/
+  # Architecture decisions live in ADRs (docs/decisions/), not curated memory.
   domain_invariants: agents/memory/domain-invariants/
   incident_learnings: agents/memory/incident-learnings/
   product_rules: agents/memory/product-rules/

package/dist/agent-src/templates/scripts/check_memory.py

@@ -50,8 +50,7 @@ REQUIRED_KEYS = {
 VALID_STATUS = {"active", "deprecated", "archived"}
 VALID_CONFIDENCE = {"low", "medium", "high"}
 KNOWN_TYPES = {
-    "domain-invariants", "architecture-decisions",
-    "incident-learnings", "product-rules",
+    "domain-invariants", "incident-learnings", "product-rules",
 }
 
 # Redaction heuristics — plain-regex, deliberately conservative.

package/dist/agent-src/templates/scripts/check_memory_proposal.py

@@ -36,7 +36,7 @@ from typing import Any
 INTAKE_ROOT = Path("agents/memory/intake")
 VALID_TYPES = {
     "historical-patterns", "incident-learnings", "ownership",
-    "domain-invariants", "architecture-decisions", "product-rules",
+    "domain-invariants", "product-rules",
 }
 REQUIRED_INTAKE = ("id", "entry_type", "path", "body")
 PATTERN_MIN_PATHS = 2