incitaciones 0.10.4 → 0.11.0

package/README.md

@@ -150,7 +150,7 @@ Workflow skills that form a complete session lifecycle with persistent operation
 | **close** | End of day | Log to journal, route knowledge to `~/.whisper/`, commit, clear |
 | **renew** | Start of session | Load journal + whisper + beads context, claim tickets with file conflict detection |
 
-Uses `$JOURNAL_PATH` (default `~/dev/status`) for the daily log. See [`content/references-whisper-workflow.md`](content/references-whisper-workflow.md) for the full reference.
+Uses `$JOURNAL_PATH` (default `~/para/areas/jornal`) for the daily log. See [`content/references-whisper-workflow.md`](content/references-whisper-workflow.md) for the full reference.
 
 Full analysis: [`content/research-finding-skill-usage-analysis.md`](content/research-finding-skill-usage-analysis.md)
 
@@ -504,7 +504,7 @@ The prompts are tool-agnostic where possible, with tool-specific variations note
 
 ## License
 
-[To be determined]
+The prompts and skills in this repository are licensed under [CC-BY-4.0](LICENSE) (Attribution 4.0 International). You are free to use, share, and adapt them with attribution.
 
 ## Related Projects
 

package/content/distilled/review/references/rule-of-5-universal/SKILL.md

@@ -17,7 +17,7 @@ Review any intellectual artifact (code, plans, research, issues, specs, document
 - **Progressive Build:** Each stage must build on previous findings.
 - **Specificity:** Reference exact locations (file:line, section, paragraph).
 - **Actionability:** Suggest specific solutions, don't just identify problems.
-- **Validation:** Confirm issues exist; do not flag "potential" issues without evidence.
+- **Validation:** Confirm issues exist; do not flag "potential" issues without evidence. If the `TYPESAFE_API_KEY` environment variable is set, apply `references/typesafe-verification.md` in place of self-reported validation. If it is not set (or the API fails), mark findings `UNVERIFIED`, print the banner defined there, and proceed with self-reported validation.
 - **Early Stop:** Stop if convergence criteria are met before Stage 5.
 
 ## References

package/content/distilled/review/references/rule-of-5-universal/references/typesafe-verification.md

@@ -0,0 +1,86 @@
+# TypeSafe Verification Pass (conditional)
+
+Use this procedure **only** when the `TYPESAFE_API_KEY` environment variable is set.
+When it is not set, or the API call fails (see Failure Handling), mark every finding
+`UNVERIFIED`, print the banner below, and fall back to self-reported validation —
+do not block the review.
+
+```
+BANNER: Findings NOT verified by TypeSafe (API unavailable or key absent).
+Self-reported validation in effect; treat false-positive estimates as unmeasured.
+```
+
+Use this procedure as-is; consult the `typesafe-ai` skill or docs.typesafe.ai only
+for SDK-language bindings beyond the HTTP call specified here. Do not re-derive
+questions, thresholds, or request shape at review time.
+
+## Constants (edit here, not inline)
+
+| Constant | Value | Notes |
+| --- | --- | --- |
+| Endpoint | `https://api.typesafe.ai/v1/systemone` | `POST`, Bearer auth |
+| Model | `jev-latest` | TypeSafe flagship alias |
+| `CONFIDENCE_GATE` | `0.8` | Tunable starting point; calibrate per workflow. Below gate → human review |
+| `VERIFY_SEVERITIES` | `CRITICAL, HIGH` | Cost cap: MEDIUM/LOW findings stay UNVERIFIED |
+| Batching | one request | All verification questions in a single parallel call |
+
+## Stage A — Mechanical pre-gate (no API)
+
+For each finding at or above `VERIFY_SEVERITIES`, check mechanically:
+
+1. Does the referenced location exist (file:line, section, paragraph)?
+2. Does any quoted evidence appear verbatim in the artifact under review?
+
+- Both pass → send to Stage B.
+- Location missing or quote absent → verdict `fabricated` **without an API call**
+  (this is a CRITICAL meta-finding about the reviewer, not the artifact).
+- No quoted evidence to check → send to Stage B anyway; the model judges context.
+
+## Stage B — One parallel verification request
+
+`state` = the artifact text plus the surviving findings (id, location, claim,
+evidence). Ask **one Choice question per finding**, all in the same request:
+
+```json
+{
+  "model": "jev-latest",
+  "state": { "artifact": "...", "findings": [ { "id": "CORR-001", "location": "...", "claim": "...", "evidence": "..." } ] },
+  "questions": {
+    "verify_CORR-001": {
+      "type": "choice",
+      "instructions": {
+        "finding": "`findings[0]`",
+        "question": "Does the `artifact` at the location named in `finding` contain evidence that supports `finding.claim`?"
+      },
+      "criteria": {
+        "verified": "The cited location contains evidence supporting the claim",
+        "unsupported": "The location exists but says nothing about the claim",
+        "contradicted": "The location's context says the opposite of the claim",
+        "fabricated": "The claim misrepresents what the location says"
+      }
+    }
+  }
+}
+```
+
+Generate one `verify_<ID>` question per finding. Never ask about multiple findings
+in one question.
+
+## Stage C — Verdict mapping
+
+| Verdict | Action |
+| --- | --- |
+| `verified`, confidence ≥ gate | Finding stands; counts toward convergence |
+| `unsupported` or `contradicted` | Drop the finding; it counts as a **measured** false positive |
+| `fabricated` (Stage A or B) | Drop; file CRITICAL meta-finding `[META-<n>]` against the review pass |
+| Any verdict with confidence < `CONFIDENCE_GATE` | Keep finding, mark `REVIEW_REQUIRED`, route to `ESCALATE_TO_HUMAN` |
+| Findings below `VERIFY_SEVERITIES` | Mark `UNVERIFIED`; excluded from FP-rate arithmetic |
+
+Convergence arithmetic (in `criteria.md`) uses these measured numbers:
+
+```
+False positive rate = dropped findings / (verified + dropped findings)
+```
+
+This replaces the self-estimated false-positive rate. Self-estimated rates are
+insufficient as a sole gate but remain one input alongside other convergence criteria.

package/content/distilled/session/references/close/SKILL.md

@@ -17,7 +17,7 @@ Uses `$JOURNAL_PATH` for the daily log journal, and `~/.whisper/` for accumulate
    JOURNAL="${JOURNAL_PATH:-$(shellval JOURNAL_PATH)}"
    [ -n "$JOURNAL" ] || JOURNAL="$(shellval JORNAL)"
    [ -n "$JOURNAL" ] || JOURNAL="$HOME/para/areas/jornal"   # JORNAL convention
-   [ -d "$JOURNAL/.git" ] || JOURNAL="$HOME/dev/status"     # legacy clone; flag this fallback in the reply
+   [ -d "$JOURNAL/.git" ] || JOURNAL="$HOME/para/areas/jornal"     # legacy clone; flag this fallback in the reply
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-$(shellval JOURNAL_LOG_SUBDIR)}"
    [ -n "$LOG_SUBDIR" ] || LOG_SUBDIR="areas/log"
    cd "$JOURNAL" && git pull

package/content/distilled/session/references/park/SKILL.md

@@ -4,13 +4,13 @@
 
 Snapshot the current session's work on a project/area before switching context. This is NOT end-of-day — just a context switch.
 
-Uses `$JOURNAL_PATH` (defaults to `~/dev/status`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
+Uses `$JOURNAL_PATH` (defaults to `~/para/areas/jornal`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
 
 ## Steps
 
 1. Get today's date and current time (`date +%Y-%m-%d`, `date +%H:%M`).
    ```bash
-   JOURNAL="${JOURNAL_PATH:-$HOME/dev/status}"
+   JOURNAL="${JOURNAL_PATH:-$HOME/para/areas/jornal}"
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-log}"
    ```
 

package/content/distilled/session/references/renew/SKILL.md

@@ -4,13 +4,13 @@
 
 Load focused context for a specific project or area to continue work.
 
-Uses `$JOURNAL_PATH` (defaults to `~/dev/status`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
+Uses `$JOURNAL_PATH` (defaults to `~/para/areas/jornal`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
 
 ## Steps
 
 1. Pull the journal repo:
    ```bash
-   JOURNAL="${JOURNAL_PATH:-$HOME/dev/status}"
+   JOURNAL="${JOURNAL_PATH:-$HOME/para/areas/jornal}"
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-log}"
    cd "$JOURNAL" && git pull
    ```

package/content/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "2026-09-28",
+  "version": "2026-09-30",
   "schema_version": "1.1",
   "prompts": [
     {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "incitaciones",
-  "version": "0.10.4",
+  "version": "0.11.0",
   "description": "Reusable prompts and skills for CLI LLM tools, with native pi package support.",
   "repository": {
     "type": "git",
@@ -10,7 +10,7 @@
   "bugs": {
     "url": "https://github.com/charly-vibes/incitaciones/issues"
   },
-  "license": "MIT",
+  "license": "CC-BY-4.0",
   "type": "module",
   "keywords": [
     "pi-package",

package/pi-package/skills/close/SKILL.md

@@ -31,7 +31,7 @@ Uses `$JOURNAL_PATH` for the daily log journal, and `~/.whisper/` for accumulate
    JOURNAL="${JOURNAL_PATH:-$(shellval JOURNAL_PATH)}"
    [ -n "$JOURNAL" ] || JOURNAL="$(shellval JORNAL)"
    [ -n "$JOURNAL" ] || JOURNAL="$HOME/para/areas/jornal"   # JORNAL convention
-   [ -d "$JOURNAL/.git" ] || JOURNAL="$HOME/dev/status"     # legacy clone; flag this fallback in the reply
+   [ -d "$JOURNAL/.git" ] || JOURNAL="$HOME/para/areas/jornal"     # legacy clone; flag this fallback in the reply
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-$(shellval JOURNAL_LOG_SUBDIR)}"
    [ -n "$LOG_SUBDIR" ] || LOG_SUBDIR="areas/log"
    cd "$JOURNAL" && git pull

package/pi-package/skills/park/SKILL.md

@@ -18,13 +18,13 @@ disable-model-invocation: true
 
 Snapshot the current session's work on a project/area before switching context. This is NOT end-of-day — just a context switch.
 
-Uses `$JOURNAL_PATH` (defaults to `~/dev/status`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
+Uses `$JOURNAL_PATH` (defaults to `~/para/areas/jornal`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
 
 ## Steps
 
 1. Get today's date and current time (`date +%Y-%m-%d`, `date +%H:%M`).
    ```bash
-   JOURNAL="${JOURNAL_PATH:-$HOME/dev/status}"
+   JOURNAL="${JOURNAL_PATH:-$HOME/para/areas/jornal}"
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-log}"
    ```
 

package/pi-package/skills/renew/SKILL.md

@@ -18,13 +18,13 @@ disable-model-invocation: true
 
 Load focused context for a specific project or area to continue work.
 
-Uses `$JOURNAL_PATH` (defaults to `~/dev/status`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
+Uses `$JOURNAL_PATH` (defaults to `~/para/areas/jornal`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
 
 ## Steps
 
 1. Pull the journal repo:
    ```bash
-   JOURNAL="${JOURNAL_PATH:-$HOME/dev/status}"
+   JOURNAL="${JOURNAL_PATH:-$HOME/para/areas/jornal}"
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-log}"
    cd "$JOURNAL" && git pull
    ```

package/pi-package/skills/review/references/rule-of-5-universal/SKILL.md

@@ -17,7 +17,7 @@ Review any intellectual artifact (code, plans, research, issues, specs, document
 - **Progressive Build:** Each stage must build on previous findings.
 - **Specificity:** Reference exact locations (file:line, section, paragraph).
 - **Actionability:** Suggest specific solutions, don't just identify problems.
-- **Validation:** Confirm issues exist; do not flag "potential" issues without evidence.
+- **Validation:** Confirm issues exist; do not flag "potential" issues without evidence. If the `TYPESAFE_API_KEY` environment variable is set, apply `references/typesafe-verification.md` in place of self-reported validation. If it is not set (or the API fails), mark findings `UNVERIFIED`, print the banner defined there, and proceed with self-reported validation.
 - **Early Stop:** Stop if convergence criteria are met before Stage 5.
 
 ## References

package/pi-package/skills/review/references/rule-of-5-universal/references/typesafe-verification.md

@@ -0,0 +1,86 @@
+# TypeSafe Verification Pass (conditional)
+
+Use this procedure **only** when the `TYPESAFE_API_KEY` environment variable is set.
+When it is not set, or the API call fails (see Failure Handling), mark every finding
+`UNVERIFIED`, print the banner below, and fall back to self-reported validation —
+do not block the review.
+
+```
+BANNER: Findings NOT verified by TypeSafe (API unavailable or key absent).
+Self-reported validation in effect; treat false-positive estimates as unmeasured.
+```
+
+Use this procedure as-is; consult the `typesafe-ai` skill or docs.typesafe.ai only
+for SDK-language bindings beyond the HTTP call specified here. Do not re-derive
+questions, thresholds, or request shape at review time.
+
+## Constants (edit here, not inline)
+
+| Constant | Value | Notes |
+| --- | --- | --- |
+| Endpoint | `https://api.typesafe.ai/v1/systemone` | `POST`, Bearer auth |
+| Model | `jev-latest` | TypeSafe flagship alias |
+| `CONFIDENCE_GATE` | `0.8` | Tunable starting point; calibrate per workflow. Below gate → human review |
+| `VERIFY_SEVERITIES` | `CRITICAL, HIGH` | Cost cap: MEDIUM/LOW findings stay UNVERIFIED |
+| Batching | one request | All verification questions in a single parallel call |
+
+## Stage A — Mechanical pre-gate (no API)
+
+For each finding at or above `VERIFY_SEVERITIES`, check mechanically:
+
+1. Does the referenced location exist (file:line, section, paragraph)?
+2. Does any quoted evidence appear verbatim in the artifact under review?
+
+- Both pass → send to Stage B.
+- Location missing or quote absent → verdict `fabricated` **without an API call**
+  (this is a CRITICAL meta-finding about the reviewer, not the artifact).
+- No quoted evidence to check → send to Stage B anyway; the model judges context.
+
+## Stage B — One parallel verification request
+
+`state` = the artifact text plus the surviving findings (id, location, claim,
+evidence). Ask **one Choice question per finding**, all in the same request:
+
+```json
+{
+  "model": "jev-latest",
+  "state": { "artifact": "...", "findings": [ { "id": "CORR-001", "location": "...", "claim": "...", "evidence": "..." } ] },
+  "questions": {
+    "verify_CORR-001": {
+      "type": "choice",
+      "instructions": {
+        "finding": "`findings[0]`",
+        "question": "Does the `artifact` at the location named in `finding` contain evidence that supports `finding.claim`?"
+      },
+      "criteria": {
+        "verified": "The cited location contains evidence supporting the claim",
+        "unsupported": "The location exists but says nothing about the claim",
+        "contradicted": "The location's context says the opposite of the claim",
+        "fabricated": "The claim misrepresents what the location says"
+      }
+    }
+  }
+}
+```
+
+Generate one `verify_<ID>` question per finding. Never ask about multiple findings
+in one question.
+
+## Stage C — Verdict mapping
+
+| Verdict | Action |
+| --- | --- |
+| `verified`, confidence ≥ gate | Finding stands; counts toward convergence |
+| `unsupported` or `contradicted` | Drop the finding; it counts as a **measured** false positive |
+| `fabricated` (Stage A or B) | Drop; file CRITICAL meta-finding `[META-<n>]` against the review pass |
+| Any verdict with confidence < `CONFIDENCE_GATE` | Keep finding, mark `REVIEW_REQUIRED`, route to `ESCALATE_TO_HUMAN` |
+| Findings below `VERIFY_SEVERITIES` | Mark `UNVERIFIED`; excluded from FP-rate arithmetic |
+
+Convergence arithmetic (in `criteria.md`) uses these measured numbers:
+
+```
+False positive rate = dropped findings / (verified + dropped findings)
+```
+
+This replaces the self-estimated false-positive rate. Self-estimated rates are
+insufficient as a sole gate but remain one input alongside other convergence criteria.

package/pi-package/skills/rule-of-5-universal/SKILL.md

@@ -31,7 +31,7 @@ Review any intellectual artifact (code, plans, research, issues, specs, document
 - **Progressive Build:** Each stage must build on previous findings.
 - **Specificity:** Reference exact locations (file:line, section, paragraph).
 - **Actionability:** Suggest specific solutions, don't just identify problems.
-- **Validation:** Confirm issues exist; do not flag "potential" issues without evidence.
+- **Validation:** Confirm issues exist; do not flag "potential" issues without evidence. If the `TYPESAFE_API_KEY` environment variable is set, apply `references/typesafe-verification.md` in place of self-reported validation. If it is not set (or the API fails), mark findings `UNVERIFIED`, print the banner defined there, and proceed with self-reported validation.
 - **Early Stop:** Stop if convergence criteria are met before Stage 5.
 
 ## References
@@ -292,3 +292,94 @@ Total Issues by Severity:
 
 **Rationale:** [1-2 sentences explaining the verdict]
 ```
+
+---
+
+#### Reference: references/typesafe-verification.md
+
+# TypeSafe Verification Pass (conditional)
+
+Use this procedure **only** when the `TYPESAFE_API_KEY` environment variable is set.
+When it is not set, or the API call fails (see Failure Handling), mark every finding
+`UNVERIFIED`, print the banner below, and fall back to self-reported validation —
+do not block the review.
+
+```
+BANNER: Findings NOT verified by TypeSafe (API unavailable or key absent).
+Self-reported validation in effect; treat false-positive estimates as unmeasured.
+```
+
+Use this procedure as-is; consult the `typesafe-ai` skill or docs.typesafe.ai only
+for SDK-language bindings beyond the HTTP call specified here. Do not re-derive
+questions, thresholds, or request shape at review time.
+
+## Constants (edit here, not inline)
+
+| Constant | Value | Notes |
+| --- | --- | --- |
+| Endpoint | `https://api.typesafe.ai/v1/systemone` | `POST`, Bearer auth |
+| Model | `jev-latest` | TypeSafe flagship alias |
+| `CONFIDENCE_GATE` | `0.8` | Tunable starting point; calibrate per workflow. Below gate → human review |
+| `VERIFY_SEVERITIES` | `CRITICAL, HIGH` | Cost cap: MEDIUM/LOW findings stay UNVERIFIED |
+| Batching | one request | All verification questions in a single parallel call |
+
+## Stage A — Mechanical pre-gate (no API)
+
+For each finding at or above `VERIFY_SEVERITIES`, check mechanically:
+
+1. Does the referenced location exist (file:line, section, paragraph)?
+2. Does any quoted evidence appear verbatim in the artifact under review?
+
+- Both pass → send to Stage B.
+- Location missing or quote absent → verdict `fabricated` **without an API call**
+  (this is a CRITICAL meta-finding about the reviewer, not the artifact).
+- No quoted evidence to check → send to Stage B anyway; the model judges context.
+
+## Stage B — One parallel verification request
+
+`state` = the artifact text plus the surviving findings (id, location, claim,
+evidence). Ask **one Choice question per finding**, all in the same request:
+
+```json
+{
+  "model": "jev-latest",
+  "state": { "artifact": "...", "findings": [ { "id": "CORR-001", "location": "...", "claim": "...", "evidence": "..." } ] },
+  "questions": {
+    "verify_CORR-001": {
+      "type": "choice",
+      "instructions": {
+        "finding": "`findings[0]`",
+        "question": "Does the `artifact` at the location named in `finding` contain evidence that supports `finding.claim`?"
+      },
+      "criteria": {
+        "verified": "The cited location contains evidence supporting the claim",
+        "unsupported": "The location exists but says nothing about the claim",
+        "contradicted": "The location's context says the opposite of the claim",
+        "fabricated": "The claim misrepresents what the location says"
+      }
+    }
+  }
+}
+```
+
+Generate one `verify_<ID>` question per finding. Never ask about multiple findings
+in one question.
+
+## Stage C — Verdict mapping
+
+| Verdict | Action |
+| --- | --- |
+| `verified`, confidence ≥ gate | Finding stands; counts toward convergence |
+| `unsupported` or `contradicted` | Drop the finding; it counts as a **measured** false positive |
+| `fabricated` (Stage A or B) | Drop; file CRITICAL meta-finding `[META-<n>]` against the review pass |
+| Any verdict with confidence < `CONFIDENCE_GATE` | Keep finding, mark `REVIEW_REQUIRED`, route to `ESCALATE_TO_HUMAN` |
+| Findings below `VERIFY_SEVERITIES` | Mark `UNVERIFIED`; excluded from FP-rate arithmetic |
+
+Convergence arithmetic (in `criteria.md`) uses these measured numbers:
+
+```
+False positive rate = dropped findings / (verified + dropped findings)
+```
+
+This replaces the self-estimated false-positive rate. Self-estimated rates are
+insufficient as a sole gate but remain one input alongside other convergence criteria.

package/pi-package/skills/session/references/close/SKILL.md

@@ -17,7 +17,7 @@ Uses `$JOURNAL_PATH` for the daily log journal, and `~/.whisper/` for accumulate
    JOURNAL="${JOURNAL_PATH:-$(shellval JOURNAL_PATH)}"
    [ -n "$JOURNAL" ] || JOURNAL="$(shellval JORNAL)"
    [ -n "$JOURNAL" ] || JOURNAL="$HOME/para/areas/jornal"   # JORNAL convention
-   [ -d "$JOURNAL/.git" ] || JOURNAL="$HOME/dev/status"     # legacy clone; flag this fallback in the reply
+   [ -d "$JOURNAL/.git" ] || JOURNAL="$HOME/para/areas/jornal"     # legacy clone; flag this fallback in the reply
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-$(shellval JOURNAL_LOG_SUBDIR)}"
    [ -n "$LOG_SUBDIR" ] || LOG_SUBDIR="areas/log"
    cd "$JOURNAL" && git pull

package/pi-package/skills/session/references/park/SKILL.md

@@ -4,13 +4,13 @@
 
 Snapshot the current session's work on a project/area before switching context. This is NOT end-of-day — just a context switch.
 
-Uses `$JOURNAL_PATH` (defaults to `~/dev/status`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
+Uses `$JOURNAL_PATH` (defaults to `~/para/areas/jornal`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
 
 ## Steps
 
 1. Get today's date and current time (`date +%Y-%m-%d`, `date +%H:%M`).
    ```bash
-   JOURNAL="${JOURNAL_PATH:-$HOME/dev/status}"
+   JOURNAL="${JOURNAL_PATH:-$HOME/para/areas/jornal}"
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-log}"
    ```
 

package/pi-package/skills/session/references/renew/SKILL.md

@@ -4,13 +4,13 @@
 
 Load focused context for a specific project or area to continue work.
 
-Uses `$JOURNAL_PATH` (defaults to `~/dev/status`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
+Uses `$JOURNAL_PATH` (defaults to `~/para/areas/jornal`) for the daily log journal, and `~/.whisper/` for accumulated operational knowledge. The log subdirectory defaults to `log/`; set `$JOURNAL_LOG_SUBDIR` to override (e.g. `areas/log` for the JORNAL layout).
 
 ## Steps
 
 1. Pull the journal repo:
    ```bash
-   JOURNAL="${JOURNAL_PATH:-$HOME/dev/status}"
+   JOURNAL="${JOURNAL_PATH:-$HOME/para/areas/jornal}"
    LOG_SUBDIR="${JOURNAL_LOG_SUBDIR:-log}"
    cd "$JOURNAL" && git pull
    ```