kibi-cursor 2.7.0 → 2.7.1

package/.cursor-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "kibi-cursor",
   "displayName": "Kibi",
-  "version": "2.7.0",
+  "version": "2.7.1",
   "description": "Optional Cursor adapter for Kibi. Requires project-local kibi-cli, kibi-mcp, and kibi-core (SWI-Prolog is bundled on Linux and macOS) before the bundled MCP server can start.",
   "license": "AGPL-3.0-or-later",
   "author": {

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # kibi-cursor
 
+## 2.7.1
+
+### Patch Changes
+
+- The bundled `kibi-usage` skill (2.16.1) now tells an agent that changes a grounded requirement's text to analyze the new prose with the requirement's `id` first, so the `Claim-key drift against the stored ledger` warning fires before any write, and it explains the two-sided proposition-complete error. Before, the Codex and Cursor packages would have kept shipping the 2.16.0 skill text after the CLI and MCP server already carried the new behavior.
+
+  Technical summary: the `skills/` mirrors in these packages are regenerated from the runtime skill canon; no code changes.
+
 ## 2.7.0
 
 ### Minor Changes

package/agent-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "kibi",
-  "version": "2.7.0",
+  "version": "2.7.1",
   "description": "Repo-local, per-branch, queryable knowledge base. Portable Agent Plugin packaging Kibi's Agent Skills and MCP server.",
   "author": { "name": "Kibi" },
   "homepage": "https://looted.github.io/kibi/",

package/agent-plugin/skills/kibi-usage/SKILL.md

@@ -2,7 +2,7 @@
 id: kibi-usage
 name: Kibi Usage
 description: Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair.
-version: 2.16.0
+version: 2.16.1
 kibiCompatibility: ">=1.0.0"
 tags:
   - kibi
@@ -286,8 +286,13 @@ authored. Each one is the order the write path accepts.
    existing entity, whose stored ledger Kibi keeps.
 2. **Changing the text of a grounded requirement.** New prose means new
    claim keys, so a bare rewrite is refused with `modeled proposition
-   claim_keys must match logical grounding target claim_keys exactly`.
-   Prefer supersession for a change of meaning: analyze the new prose,
+   claim_keys must match logical grounding target claim_keys exactly`; the
+   error names the modeled keys no fact declares and the facts whose keys
+   the ledger dropped. Analyze the new prose with the requirement's `id`
+   first: the receipt warns `Claim-key drift against the stored ledger`
+   and names the grounded clauses the new wording drops (the title worded
+   differently from the stored `semantic_text` is the usual cause), before
+   any write. Prefer supersession for a change of meaning: analyze the new prose,
    write its facts, write the new requirement (`-v2`) with `supersedes` to
    the old one, then set the old one to `status: closed`. Its scenario
    follows the same rule as in recipe 1: create the new scenario (with

package/dist/.cursor-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "kibi-cursor",
   "displayName": "Kibi",
-  "version": "2.7.0",
+  "version": "2.7.1",
   "description": "Optional Cursor adapter for Kibi. Requires project-local kibi-cli, kibi-mcp, and kibi-core (SWI-Prolog is bundled on Linux and macOS) before the bundled MCP server can start.",
   "license": "AGPL-3.0-or-later",
   "author": {

package/dist/skills/.canon-hash.json

@@ -13,7 +13,7 @@
   "kibi-traceability/resources/operation-access.md": "39f7972ab7f4ae7479e78f7072bb50e8e6c4cdf4f857425f69d2522d37db437c",
   "kibi-traceability/resources/source-authoring.md": "408c6ee2bef1b84e0194c0538ef929c26a0a617e631b2234247388140dbbdd08",
   "kibi-traceability/resources/traceability.md": "38c290a0bc71bd1692e115f22694743946e2f69630e134acfd43cee5f613fb88",
-  "kibi-usage/SKILL.md": "cc1ad5253a21ba6ceb998714cb908925bae14cf29af0c4f7f230c6ed6556a2bc",
+  "kibi-usage/SKILL.md": "4726d657b799e52f71810985287e3ba42a79a80a8d69c733a3eaa63120de3d27",
   "kibi-usage/resources/branch-lifecycle.md": "f1bf359e9826e83c548f3cd0287f8175a62456527b0132b06b3f9f74aa59b7d6",
   "kibi-usage/resources/fact-lanes.md": "899218f90396aa469b6e34aeb5f7ea1f38bf11bb326102319f376c213859fb33",
   "kibi-usage/resources/kb-improvement.md": "a8408fce27342bdce6415a6718599e53fe00bb33aa1fd3dc42353ec6f61adcd7",

package/dist/skills/kibi-usage/SKILL.md

@@ -2,7 +2,7 @@
 id: kibi-usage
 name: Kibi Usage
 description: Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair.
-version: 2.16.0
+version: 2.16.1
 kibiCompatibility: ">=1.0.0"
 tags:
   - kibi
@@ -286,8 +286,13 @@ authored. Each one is the order the write path accepts.
    existing entity, whose stored ledger Kibi keeps.
 2. **Changing the text of a grounded requirement.** New prose means new
    claim keys, so a bare rewrite is refused with `modeled proposition
-   claim_keys must match logical grounding target claim_keys exactly`.
-   Prefer supersession for a change of meaning: analyze the new prose,
+   claim_keys must match logical grounding target claim_keys exactly`; the
+   error names the modeled keys no fact declares and the facts whose keys
+   the ledger dropped. Analyze the new prose with the requirement's `id`
+   first: the receipt warns `Claim-key drift against the stored ledger`
+   and names the grounded clauses the new wording drops (the title worded
+   differently from the stored `semantic_text` is the usual cause), before
+   any write. Prefer supersession for a change of meaning: analyze the new prose,
    write its facts, write the new requirement (`-v2`) with `supersedes` to
    the old one, then set the old one to `status: closed`. Its scenario
    follows the same rule as in recipe 1: create the new scenario (with

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "kibi-cursor",
-  "version": "2.7.0",
+  "version": "2.7.1",
   "description": "Kibi Cursor plugin - thin adapter for Cursor MCP integration and editor hooks",
   "type": "module",
   "main": "dist/index.js",

package/skills/.canon-hash.json

@@ -13,7 +13,7 @@
   "kibi-traceability/resources/operation-access.md": "39f7972ab7f4ae7479e78f7072bb50e8e6c4cdf4f857425f69d2522d37db437c",
   "kibi-traceability/resources/source-authoring.md": "408c6ee2bef1b84e0194c0538ef929c26a0a617e631b2234247388140dbbdd08",
   "kibi-traceability/resources/traceability.md": "38c290a0bc71bd1692e115f22694743946e2f69630e134acfd43cee5f613fb88",
-  "kibi-usage/SKILL.md": "cc1ad5253a21ba6ceb998714cb908925bae14cf29af0c4f7f230c6ed6556a2bc",
+  "kibi-usage/SKILL.md": "4726d657b799e52f71810985287e3ba42a79a80a8d69c733a3eaa63120de3d27",
   "kibi-usage/resources/branch-lifecycle.md": "f1bf359e9826e83c548f3cd0287f8175a62456527b0132b06b3f9f74aa59b7d6",
   "kibi-usage/resources/fact-lanes.md": "899218f90396aa469b6e34aeb5f7ea1f38bf11bb326102319f376c213859fb33",
   "kibi-usage/resources/kb-improvement.md": "a8408fce27342bdce6415a6718599e53fe00bb33aa1fd3dc42353ec6f61adcd7",

package/skills/kibi-usage/SKILL.md

@@ -2,7 +2,7 @@
 id: kibi-usage
 name: Kibi Usage
 description: Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair.
-version: 2.16.0
+version: 2.16.1
 kibiCompatibility: ">=1.0.0"
 tags:
   - kibi
@@ -286,8 +286,13 @@ authored. Each one is the order the write path accepts.
    existing entity, whose stored ledger Kibi keeps.
 2. **Changing the text of a grounded requirement.** New prose means new
    claim keys, so a bare rewrite is refused with `modeled proposition
-   claim_keys must match logical grounding target claim_keys exactly`.
-   Prefer supersession for a change of meaning: analyze the new prose,
+   claim_keys must match logical grounding target claim_keys exactly`; the
+   error names the modeled keys no fact declares and the facts whose keys
+   the ledger dropped. Analyze the new prose with the requirement's `id`
+   first: the receipt warns `Claim-key drift against the stored ledger`
+   and names the grounded clauses the new wording drops (the title worded
+   differently from the stored `semantic_text` is the usual cause), before
+   any write. Prefer supersession for a change of meaning: analyze the new prose,
    write its facts, write the new requirement (`-v2`) with `supersedes` to
    the old one, then set the old one to `status: closed`. Its scenario
    follows the same rule as in recipe 1: create the new scenario (with