kibi-cursor 2.10.0 → 2.11.0

package/dist/skills/kibi-decisions/resources/signoff-views.md

@@ -51,7 +51,9 @@ writes and opens the page; `--format json` prints the view.
 The person answers by number ("1 yes, 2 exploratory, 3 reword: ..."). Copy
 each answer into `answer`, render again, and record the rules only once every
 question is answered. An answer is the person's words: quote it in
-`origin.ref`; a view itself is never an approval.
+`origin.ref`; a view itself is never an approval. Record the answers on the
+branch of the change they approve and push them to its pull request, never to
+a separate one.
 
 ## Summary contents
 

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: 2.36.0
+version: 2.40.1
 kibiCompatibility: ">=1.0.0"
 tags:
   - kibi
@@ -20,6 +20,7 @@ resources:
   - resources/fact-lanes.md
   - resources/workflows.md
   - resources/proof.md
+  - resources/prolog-proofs.md
   - resources/ui-requirements.md
   - resources/logic-ir.md
   - resources/kb-improvement.md
@@ -94,8 +95,10 @@ it is a pointer to the knowledge, never proof. Each line answers one question:
   requirement first. Read the lead requirement with `kb_query({id})` before
   changing behavior; add `includeBody: true` to see its authored prose, and
   fix a stale sentence there with `kb_upsert` `document.body`.
-- `REQ-… must keep true: FACT-…` (edit only): the ground facts the lead
-  requirement requires. An edit that breaks one of them is a requirement
+- `REQ-… must keep true: <claim>` (edit only): what the lead requirement
+  requires, as the claims its facts model (with the operator and members,
+  such as "The greet function must not call console.log") or, without
+  them, its own statement. An edit that breaks one of them is a requirement
   change: ask before changing the rule (see Decision firmness), and never
   code around the fact.
 - `Decision: ADR-…` (edit only): the decision behind the lead requirement.
@@ -372,6 +375,14 @@ human sets `approved_by`; `kb_check` flags approvals an agent recorded without
 corroboration. Never fill in an approval yourself. Record why a requirement
 exists in `rationale`, or link the ADR that explains it.
 
+A signoff belongs to the change it approves. Ask for it before you open or
+merge the pull request, and when the person answers, record their answer
+(`approved_by` or a `*_waiver_approved_by` field set to them, their words in
+`origin.ref` or `approval_ref`) on the same branch and push it to the same pull
+request. Writing down an answer the person gave is not approving it yourself.
+Never open a separate pull request only to carry a signoff, firmness or waiver
+approval.
+
 ## Decision firmness
 
 Requirements and ADRs carry `firmness`, which says what you may do with them.

package/dist/skills/kibi-usage/resources/prolog-proofs.md

@@ -0,0 +1,207 @@
+# SWI-Prolog Code Proofs
+
+Kibi reads code models from SWI-Prolog files (`.pl`, `.plt`) with the
+SWI-Prolog it runs on (KIBI_SWIPL, the bundled runtime, then `swipl` on
+PATH). It loads the file a symbol names (a module, or a plain file into
+`user`) and reads a predicate named by its indicator, the symbol's title
+(`operator/2`, `lists:append/3`, `greeting//1`) or `export`.
+
+- A domain (`exhaustive`, `domains`, `value_source` with `measure: count`)
+  is the distinct solutions of one argument. A one-argument predicate needs
+  nothing more; for more arguments set `arg` (1-based) to the one that names
+  each member: `domain_source: {symbol_id: SYM-operator, arg: 1}` lists every
+  `Name` of `operator(Name, Description)`. A solution that leaves that
+  argument unbound refuses the read.
+- A value (`value_source`) is the single number a constant holds:
+  `hard_limit_seconds(10).` Zero or several solutions refuse the read.
+- A `rule` predicate is called once per row of its argument domains; success
+  is true, failure false, an exception an error row (which rejects).
+- A `state_machine` transition table is a `Name/2` (from, to) or `Name/3`
+  (from, event, to) fact table: every solution is an edge. With `domains:
+  {state, event}` a `Name/3` next-state predicate is called on every state
+  and event. `initial_source` names an `initial/1`-style fact.
+- A `regex` reads an atom or string constant as a `type: string` pattern;
+  Kibi decides string facts on it. Patterns for `library(pcre)` are not read.
+
+Loading a module runs its directives, the same trust a JavaScript import
+gives. The proof file must name the predicate and load its file
+(`use_module`, `ensure_loaded`, `consult`, a `:- [..]` load list, or
+`library(X)` for a pack's `prolog/X.pl`), or be the plunit `.plt` file
+beside it; otherwise Kibi treats the domain as hand-listed. `arg` on a
+TypeScript, JavaScript or Python export is refused, and so is `field` on a
+Prolog predicate.
+
+## Writing the certificate
+
+A Prolog test writes the `kibi.code-certificate.v1` JSON into the directory
+`kibi prove` sets in `KIBI_PROOF_CERTIFICATES`. Copy this module into the
+project's test directory (for example `test/kibi_certificate.pl`) and call it
+from the proof. Read members from the code with `findall/3` over the domain
+predicate; never list them by hand.
+
+```prolog
+:- module(kibi_certificate,
+          [ kibi_exhaustive_certificate/5,  % +TestId, +SymbolId, +Members, :Check, -Certificate
+            kibi_rule_certificate/4,        % +TestId, +Domains, +Predicates, -Certificate
+            kibi_machine_certificate/5,     % +TestId, +SymbolId, +Edges, +Initial, -Certificate
+            kibi_pattern_certificate/4,     % +TestId, +SymbolId, +Text, -Certificate
+            kibi_write_certificate/1        % +Certificate
+          ]).
+:- use_module(library(http/json)).
+:- use_module(library(apply)).
+:- use_module(library(lists)).
+
+:- meta_predicate
+    kibi_exhaustive_certificate(+, +, +, 1, -).
+
+% Members as Kibi reads them: atoms and strings as text, numbers as written,
+% other terms quoted.
+kibi_text(Value, Text) :- string(Value), !, Text = Value.
+kibi_text(Value, Text) :- atom(Value), !, atom_string(Value, Text).
+kibi_text(Value, Text) :- number(Value), !, number_string(Value, Text).
+kibi_text(Value, Text) :- format(string(Text), "~q", [Value]).
+
+%!  kibi_exhaustive_certificate(+TestId, +SymbolId, +Members, :Check, -Certificate)
+%
+%   Run Check on every member of the domain and record each outcome. Read
+%   Members from the code (findall over the domain predicate), never list
+%   them by hand: Kibi re-reads the predicate and rejects a different set.
+kibi_exhaustive_certificate(TestId, SymbolId, Members, Check, Certificate) :-
+    maplist(kibi_text, Members, Texts),
+    maplist(exhaustive_result(Check), Members, Texts, Results),
+    Certificate = _{version: "kibi.code-certificate.v1", kind: "exhaustive",
+                    test_id: TestId,
+                    domain: _{symbol_id: SymbolId, members: Texts},
+                    results: Results}.
+
+exhaustive_result(Check, Member, Text, Result) :-
+    catch(( call(Check, Member)
+          -> Result = _{member: Text, outcome: "passed"}
+          ;  Result = _{member: Text, outcome: "failed", message: "the check failed"}
+          ),
+          Error,
+          ( message_to_text(Error, Message),
+            Result = _{member: Text, outcome: "failed", message: Message} )).
+
+%!  kibi_rule_certificate(+TestId, +Domains, +Predicates, -Certificate)
+%
+%   Domains is a list of domain(Type, SymbolId, Members); Predicates a list
+%   of predicate(Name, SymbolId, ArgTypes, Goal), where Goal is called with
+%   one argument per type appended and decides the row by success or
+%   failure.
+kibi_rule_certificate(TestId, Domains, Predicates, Certificate) :-
+    findall(Type-_{symbol_id: SymbolId, members: Texts},
+            ( member(domain(Type, SymbolId, Members), Domains), maplist(kibi_text, Members, Texts) ),
+            DomainPairs),
+    dict_pairs(DomainDict, _, DomainPairs),
+    findall(Name-_{symbol_id: SymbolId, arg_types: ArgTypes, rows: Rows},
+            ( member(predicate(Name, SymbolId, ArgTypes, Goal), Predicates),
+              maplist(domain_members(Domains), ArgTypes, Lists),
+              findall(Row, (maplist(member, Tuple, Lists), rule_row(Goal, Tuple, Row)), Rows)
+            ),
+            PredicatePairs),
+    dict_pairs(PredicateDict, _, PredicatePairs),
+    Certificate = _{version: "kibi.code-certificate.v1", kind: "rule",
+                    test_id: TestId, domains: DomainDict, predicates: PredicateDict}.
+
+domain_members(Domains, Type, Members) :-
+    memberchk(domain(Type, _, Members), Domains).
+
+rule_row(Goal, Tuple, Row) :-
+    maplist(kibi_text, Tuple, Args),
+    Call =.. [call, Goal|Tuple],
+    catch(( once(Call) -> Row = _{args: Args, value: true} ; Row = _{args: Args, value: false} ),
+          Error,
+          ( message_to_text(Error, Message), Row = _{args: Args, error: Message} )).
+
+%!  kibi_machine_certificate(+TestId, +SymbolId, +Edges, +Initial, -Certificate)
+%
+%   Edges is the list of From-To pairs of the transition table (findall over
+%   it); Initial is the list of initial states, or [] when the contract names
+%   no initial_source.
+kibi_machine_certificate(TestId, SymbolId, Edges, Initial, Certificate) :-
+    findall([F, T], (member(From-To, Edges), kibi_text(From, F), kibi_text(To, T)), Pairs0),
+    sort(Pairs0, Pairs),
+    findall(S, (member([A, B], Pairs), member(S, [A, B])), Ends),
+    sort(Ends, States),
+    Machine0 = _{symbol_id: SymbolId, states: States, transitions: Pairs},
+    (   Initial == []
+    ->  Machine = Machine0
+    ;   maplist(kibi_text, Initial, InitialTexts0),
+        sort(InitialTexts0, InitialTexts),
+        Machine = Machine0.put(initial, InitialTexts)
+    ),
+    Certificate = _{version: "kibi.code-certificate.v1", kind: "state_machine",
+                    test_id: TestId, machine: Machine}.
+
+%!  kibi_pattern_certificate(+TestId, +SymbolId, +Text, -Certificate)
+%
+%   The string or atom constant a string claim is about.
+kibi_pattern_certificate(TestId, SymbolId, Value, Certificate) :-
+    kibi_text(Value, Text),
+    Certificate = _{version: "kibi.code-certificate.v1", kind: "regex", test_id: TestId,
+                    pattern: _{symbol_id: SymbolId, type: "string", value: Text}}.
+
+%!  kibi_write_certificate(+Certificate)
+%
+%   Leave the certificate where kibi prove reads it (the directory in
+%   KIBI_PROOF_CERTIFICATES). Does nothing outside a kibi prove run.
+kibi_write_certificate(Certificate) :-
+    (   getenv('KIBI_PROOF_CERTIFICATES', Directory), Directory \== ''
+    ->  make_directory_path(Directory),
+        format(atom(Name), "~w.json", [Certificate.test_id]),
+        directory_file_path(Directory, Name, File),
+        setup_call_cleanup(open(File, write, Out, [encoding(utf8)]),
+                           json_write_dict(Out, Certificate, [width(0)]),
+                           close(Out))
+    ;   true
+    ).
+
+message_to_text(Error, Text) :-
+    catch(message_to_codes(Error, Text), _, fail), !.
+message_to_text(Error, Text) :- format(string(Text), "~q", [Error]).
+
+message_to_codes(Error, Text) :-
+    '$messages':translate_message(Error, Lines, []),
+    with_output_to(string(Raw), print_message_lines(current_output, '', Lines)),
+    split_string(Raw, "", "\n ", [Text]).
+```
+
+A proof that the operators are exactly the claimed set:
+
+```prolog
+:- use_module('../prolog/operators').
+:- use_module(kibi_certificate).
+:- initialization(main, main).
+
+main :-
+    findall(Name, operator(Name, _), Names0),
+    list_to_set(Names0, Names),
+    kibi_exhaustive_certificate('TEST-operator-set', 'SYM-operator', Names,
+                                [Name]>>operator(Name, _), Certificate),
+    kibi_write_certificate(Certificate).
+```
+
+Its contract: `kind: exhaustive`, `domain_source: {symbol_id: SYM-operator,
+arg: 1}`, `proves: [CLAIM-...]`. A rule proof passes
+`[domain(status, 'SYM-status', Statuses)]` and
+`[predicate(detected, 'SYM-detected', [status], detected)]`; its contract
+names `predicate_source: {detected: {symbol_id: SYM-detected}}` and
+`domains: {status: {symbol_id: SYM-status}}`.
+
+## Source proofs over Prolog code
+
+A `source` proof needs no certificate: Kibi reads the Prolog files itself,
+term by term, and never runs them. Use the `references` reader on `.pl` and
+`.plt` files for what modules load (`extract: imports`, members as written:
+`library(lists)`, `helpers`), call (`calls`, `Name/Arity` or
+`Module:Name/Arity`), read from the environment (`env`, `getenv/2`), pass as
+a first argument (`string_args` with `callee`) and throw (`thrown`: the error
+of `error(type_error(...), _)` is `type_error`). Use the `prolog` reader for
+facts: `{reader: prolog, file: pack.pl, functor: requires/1}` lists a pack's
+requirements, and `arg` picks the argument of a fact with several. A goal or
+closure held in a variable (`call(Goal)`, `maplist(G, L)`), a goal with a
+variable module, a clause asserted from a variable and `:- if(...)` fail the
+read with their place: name the predicate instead. The claim cannot be
+decided for a file the read refuses; never drop a file the claim is about
+from `files`.

package/dist/skills/kibi-usage/resources/proof.md

@@ -262,11 +262,15 @@ left:
   each list item, such as the `run` of each workflow step), `glob` (`pattern`, `capture`),
   `openapi` (`file`, `select: operations|unsecured_operations|...`),
   `references` (`files`, `extract: env|imports|calls|string_args|thrown|
-  property`), `schema` (`format: drizzle|prisma|sql`, `select:
+  property`; TypeScript, JavaScript, Python and SWI-Prolog files, and Go,
+  Java, C# and Rust files through `kibi-plugin-treesitter`), `schema` (`format: drizzle|prisma|sql`, `select:
   tables|columns|required_columns|nullable_columns|foreign_keys`), `routes`
   (Hono or Express app export, `path_prefix`, `names_from`, `select:
   routes|middleware`) or `validator` (zod, valibot or pydantic, `select:
-  fields|required_fields|optional_fields`). A member Kibi cannot read
+  fields|required_fields|optional_fields`) or `prolog` (`file`, `functor:
+  requires/1`, `arg`: one argument of each fact, such as a pack's
+  requirements in `pack.pl`). Prolog files are read term by term and never
+  run; see `resources/prolog-proofs.md`. A member Kibi cannot read
   statically (a computed env name, a dynamic import, an env object handed
   to a variable) fails the read with its location, and so does an empty
   read (a glob matching no file, migrations with no `CREATE TABLE`), so a
@@ -288,6 +292,40 @@ left:
   The builders need kibi-cli 2.33.0 or newer in the project. The env
   extractor reads `process.env`, `import.meta.env`, `Bun.env`,
   `Deno.env.get`, `os.environ` and `os.getenv`, through casts.
+- `references` over Go, Java, C# or Rust needs `kibi-plugin-treesitter` and
+  the language's grammar pack (`kibi-lang-go`, `kibi-lang-java`,
+  `kibi-lang-csharp`, `kibi-lang-rust`) in `devDependencies`, with the
+  plugin activated for proofs:
+  `"kibi.reference-extractor.v1": { "mode": "augment" }` in its
+  `kibi.plugins` entry (next to `"kibi.symbol-extractor.v2"`). A project
+  with no `package.json` creates one that only holds this list. Without it
+  the read is refused with what to install, so ask the operator before
+  installing; `kibi doctor` names what the project needs. Members are
+  written as the code names them (`os.Getenv`, `System.out.println`,
+  `Console.WriteLine`, `std::env::var`, Go import paths, `java.util.*`,
+  `std::io::Write`); a method on an expression Kibi cannot name is
+  `*.name`. Reflection, a name computed at run time, the whole
+  environment, C# `dynamic` and `#if`, Rust `#[cfg(...)]` items other than
+  `#[cfg(test)]`, and any macro for Rust `calls` and `thrown` fail the
+  read with their place: the claim cannot be decided for that file, so
+  model a claim the code can show (Rust `calls` over a file with
+  `println!` is always refused). Never drop a file the claim is about
+  from `files`: the read decides a claim only for the files it covers,
+  and a proof is rejected when a symbol the test covers or that
+  implements the claim's requirement lies outside them.
+- Reference members match by name segments (`.`, `/`, `::`). `excludes`
+  fails on anything that is or may be an excluded item: `java.sql`
+  excludes `java.sql.Connection`, `github.com/labstack/echo/v4` excludes
+  `.../echo/v4/middleware`, a trailing `*` is a prefix (`java.sql.*`), a
+  wildcard import or a shorter name (`File.delete`) may be the item, and
+  `*.delete` (a call on a receiver Kibi cannot name) may be
+  `java.io.File.delete`, so the claim is refused naming it. `includes` and
+  `subset_of` count only members that certainly are an item (the item, a
+  member under `X.*`, or `a.b.m` for `*.m`); `eq` compares spellings.
+- For a claim about what the code reads from the environment use
+  `extract: env`: `string_args` on a getter (`os.Getenv`, `env::var`,
+  `System.getenv`, `getenv/2`, ...) sees only that getter, so Kibi refuses
+  it for `eq`, `subset_of` and `excludes`.
 
 `arithmetic` and `smt` from `constraint_source` alone prove that the
 knowledge base's facts entail the claim, not that code follows the facts:
@@ -318,7 +356,10 @@ read for a test that wants to assert on it), fail the test when it records a fai
 (`failedMembers`, `failedCalls`), and call `writeCodeCertificate`; it writes to the
 directory `kibi prove` sets in `KIBI_PROOF_CERTIFICATES` and does nothing
 elsewhere. A Python test writes the same `kibi.code-certificate.v1` JSON
-to that directory itself. Wire the KB: the proof file symbol is
+to that directory itself. Kibi also reads SWI-Prolog domains, constants,
+rule predicates, transition tables and string constants (`arg` picks a
+predicate's argument); `resources/prolog-proofs.md` has the rules and a
+certificate module to copy. Wire the KB: the proof file symbol is
 `executable_for` the test and named in `required_proofs`; the domain symbol
 (and every symbol a rule, machine or pattern contract names) `implements`
 the requirement and is `covered_by` the test; the test

package/hooks/hooks.json

@@ -3,32 +3,32 @@
   "hooks": {
     "sessionStart": [
       {
-        "command": "node dist/hook-runner.js"
+        "command": "node bin/hook-runner.mjs"
       }
     ],
     "beforeSubmitPrompt": [
       {
-        "command": "node dist/hook-runner.js"
+        "command": "node bin/hook-runner.mjs"
       }
     ],
     "preToolUse": [
       {
-        "command": "node dist/hook-runner.js"
+        "command": "node bin/hook-runner.mjs"
       }
     ],
     "postToolUse": [
       {
-        "command": "node dist/hook-runner.js"
+        "command": "node bin/hook-runner.mjs"
       }
     ],
     "beforeReadFile": [
       {
-        "command": "node dist/hook-runner.js"
+        "command": "node bin/hook-runner.mjs"
       }
     ],
     "stop": [
       {
-        "command": "node dist/hook-runner.js",
+        "command": "node bin/hook-runner.mjs",
         "loop_limit": 1
       }
     ]

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "kibi-cursor",
-  "version": "2.10.0",
+  "version": "2.11.0",
   "description": "Kibi Cursor plugin - thin adapter for Cursor MCP integration and editor hooks",
   "type": "module",
   "main": "dist/index.js",
@@ -41,7 +41,9 @@
     "access": "public"
   },
   "scripts": {
-    "build": "tsc -p tsconfig.json && bun run scripts/copy-plugin-assets.ts && bun run scripts/build-agent-plugin.ts && bun run ../../scripts/sync-agent-skills.ts --write --target cursor",
+    "build": "tsc -p tsconfig.json && bun run build:hook-bundle && bun run scripts/copy-plugin-assets.ts && bun run scripts/build-agent-plugin.ts && bun run ../../scripts/sync-agent-skills.ts --write --target cursor",
+    "build:hook-bundle": "bun run scripts/build-hook-bundle.ts",
+    "check:hook-bundle": "bun run --cwd ../agent-core build && bun run scripts/build-hook-bundle.ts --check",
     "dev": "tsc -p tsconfig.json --watch",
     "clean": "rm -rf dist",
     "prepack": "npm run build"
@@ -59,7 +61,7 @@
     }
   },
   "dependencies": {
-    "kibi-agent-core": "^0.10.0"
+    "kibi-agent-core": "^0.11.1"
   },
   "devDependencies": {
     "@types/node": "latest",

package/skills/.canon-hash.json

@@ -4,11 +4,11 @@
   "kibi-bootstrap/resources/branch-lifecycle.md": "c854264ce888439140883a3fc636db5e522f020dd27b30a5c1ecc4105b64ed13",
   "kibi-bootstrap/resources/operation-access.md": "b5a6a59e72d800c376e7fad79132897623c32a0ce152a1e8d73f9628b444db51",
   "kibi-bootstrap/resources/source-authoring.md": "bf296e62f69474e01797d6cb9469bf624551dca834dd188abb6e705bd96fa586",
-  "kibi-commit-review/SKILL.md": "cd3a0d5ed5e2e7562995180e440dce1aa1607d3d072d3400e966e988725ed399",
+  "kibi-commit-review/SKILL.md": "bec768ad3e4cd4e782e9e13360b69bcd40a0964b305909818115d7f9e8d282d9",
   "kibi-commit-review/resources/staged-gate.md": "37f750f327bb9202c1f30989763f4f1205b906cf672318ca50887d7984bc3e08",
-  "kibi-decisions/SKILL.md": "02685fa50f093025782986bfe009940e934c3a64d47858920815e7eb66b0c523",
+  "kibi-decisions/SKILL.md": "d91f784410251095e9d881bce751728cc4596858a518fb24f5e5d38c940bab50",
   "kibi-decisions/resources/decision-records.md": "b201e619c48daf6ebe5989991a96f6c0573adb6c37abf814b9d34b7a1cd423c6",
-  "kibi-decisions/resources/signoff-views.md": "123da13a3f2b30b5672044a1284626e218d3088411f84f2692746f95e06c1393",
+  "kibi-decisions/resources/signoff-views.md": "84eb2b7123e54047205b84af6fbf60c910ebcaaf98023e5812f3de9b65a4871c",
   "kibi-freshness/SKILL.md": "b5c4f24bebdb5b4e0d04c2fa1176fc33ace35334b0c0b6ca943d6f445dc9b69e",
   "kibi-freshness/resources/branch-lifecycle.md": "ebc01b19fe3dca8df5fc0175978963f6f1204f71f7c805cb2a5fb1b277ac78e4",
   "kibi-freshness/resources/operation-access.md": "4e1db9294ee540cd29b8b3a2532a81e7894d5b4228b39e99ba48b37212f489f3",
@@ -18,13 +18,14 @@
   "kibi-traceability/resources/operation-access.md": "39f7972ab7f4ae7479e78f7072bb50e8e6c4cdf4f857425f69d2522d37db437c",
   "kibi-traceability/resources/source-authoring.md": "408c6ee2bef1b84e0194c0538ef929c26a0a617e631b2234247388140dbbdd08",
   "kibi-traceability/resources/traceability.md": "38c290a0bc71bd1692e115f22694743946e2f69630e134acfd43cee5f613fb88",
-  "kibi-usage/SKILL.md": "d5c2e9e2e643f51f068a4e586002976d28125001c33e791e70994efdbbc8130f",
+  "kibi-usage/SKILL.md": "91639d49eae60a83b01017de1843ce49575db231f3f9cb1b0270c57a20462a88",
   "kibi-usage/resources/branch-lifecycle.md": "f1bf359e9826e83c548f3cd0287f8175a62456527b0132b06b3f9f74aa59b7d6",
   "kibi-usage/resources/fact-lanes.md": "7d487ffb794f6a7c32afabc7756a265a258b072ca83510ddb40d275863d44648",
   "kibi-usage/resources/kb-improvement.md": "a8408fce27342bdce6415a6718599e53fe00bb33aa1fd3dc42353ec6f61adcd7",
   "kibi-usage/resources/logic-ir.md": "0e8ce8aad07433ab4803ec169149ff6c4e1cf8cf010af18fa6fd67862d9be807",
   "kibi-usage/resources/operation-access.md": "eb455796c066787ffd3fae8db0db1d3e87a84265a57f06ae61e30103cd6aed66",
-  "kibi-usage/resources/proof.md": "65797125425f457dd6291e034e4174166bc0b62a2c269d136877c6f8de676bf0",
+  "kibi-usage/resources/prolog-proofs.md": "b630f1edf32c4d14dbd096deb15c370f6ce05dede8aa9cda4fbf294d8668f164",
+  "kibi-usage/resources/proof.md": "fe5c0ed8117ec724f925c29a95345e2f7b9969a413a3ba56eece23273f91346e",
   "kibi-usage/resources/relationship-directions.md": "0fdd67032c2d15299f772845fc4f807eb9435b09507bd87a5911ab33db2f143d",
   "kibi-usage/resources/source-authoring.md": "cad93f1e0ae08a676f2de7492f9227677880302327e74d159618fea86ca50abe",
   "kibi-usage/resources/ui-requirements.md": "f99c2a9a73bbb7bd92ce1f231db3056d544588be149a5b0d3f7cc6f28bc9eee9",

package/skills/kibi-commit-review/SKILL.md

@@ -2,7 +2,7 @@
 id: kibi-commit-review
 name: kibi-commit-review
 description: "Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, and how merge commits and migration renames are judged."
-version: 1.3.0
+version: 1.4.0
 kibiCompatibility: ">=1.0.0"
 tags:
   - kibi
@@ -91,7 +91,11 @@ apps); never attach the `.html` as a file, which chat apps show as raw source;
 past 15 requirements the Markdown stops and only the page lists them all.
 Host details: `kibi-decisions`, `resources/signoff-views.md`. `--no-proof` skips the proof lookup, which reads coverage and is slow
 on a large knowledge base. The summary is not an approval: never set
-`approved_by` or `origin.ref` from it.
+`approved_by` or `origin.ref` from it. Show it before you open or merge the
+pull request. When the person answers, record their answer in the same
+change (their name in `approved_by`, their words in `origin.ref` or
+`approval_ref`) and push it to the same pull request; never move a signoff,
+firmness or waiver approval into a separate pull request.
 
 ## Impact reviews
 

package/skills/kibi-decisions/SKILL.md

@@ -2,7 +2,7 @@
 id: kibi-decisions
 name: kibi-decisions
 description: "Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, and putting decisions to the person as one numbered kibi signoff --questions view."
-version: 1.4.0
+version: 1.5.0
 kibiCompatibility: ">=1.0.0"
 tags:
   - kibi
@@ -115,7 +115,12 @@ again until none is open, then record each rule with their words in
 `origin.ref`. Fields and outputs: `resources/signoff-views.md`.
 
 Never invent words for `origin.ref`, never set `approved_by` yourself, and
-mark your own picks `default` and guesses `exploratory`. Payload shapes,
+mark your own picks `default` and guesses `exploratory`. Once the person has
+answered, recording their answer (their name in `approved_by` or a
+`*_waiver_approved_by` field, their words in `origin.ref` or `approval_ref`)
+is yours to do: put it on the branch of the change it approves and push it to
+that pull request, never to a separate one. Ask before you open or merge the
+pull request, so the answer lands in it. Payload shapes,
 refusal messages and the `kb_compile_intent` review loop are in
 `resources/decision-records.md`.
 

package/skills/kibi-decisions/resources/signoff-views.md

@@ -51,7 +51,9 @@ writes and opens the page; `--format json` prints the view.
 The person answers by number ("1 yes, 2 exploratory, 3 reword: ..."). Copy
 each answer into `answer`, render again, and record the rules only once every
 question is answered. An answer is the person's words: quote it in
-`origin.ref`; a view itself is never an approval.
+`origin.ref`; a view itself is never an approval. Record the answers on the
+branch of the change they approve and push them to its pull request, never to
+a separate one.
 
 ## Summary contents
 

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: 2.36.0
+version: 2.40.1
 kibiCompatibility: ">=1.0.0"
 tags:
   - kibi
@@ -20,6 +20,7 @@ resources:
   - resources/fact-lanes.md
   - resources/workflows.md
   - resources/proof.md
+  - resources/prolog-proofs.md
   - resources/ui-requirements.md
   - resources/logic-ir.md
   - resources/kb-improvement.md
@@ -94,8 +95,10 @@ it is a pointer to the knowledge, never proof. Each line answers one question:
   requirement first. Read the lead requirement with `kb_query({id})` before
   changing behavior; add `includeBody: true` to see its authored prose, and
   fix a stale sentence there with `kb_upsert` `document.body`.
-- `REQ-… must keep true: FACT-…` (edit only): the ground facts the lead
-  requirement requires. An edit that breaks one of them is a requirement
+- `REQ-… must keep true: <claim>` (edit only): what the lead requirement
+  requires, as the claims its facts model (with the operator and members,
+  such as "The greet function must not call console.log") or, without
+  them, its own statement. An edit that breaks one of them is a requirement
   change: ask before changing the rule (see Decision firmness), and never
   code around the fact.
 - `Decision: ADR-…` (edit only): the decision behind the lead requirement.
@@ -372,6 +375,14 @@ human sets `approved_by`; `kb_check` flags approvals an agent recorded without
 corroboration. Never fill in an approval yourself. Record why a requirement
 exists in `rationale`, or link the ADR that explains it.
 
+A signoff belongs to the change it approves. Ask for it before you open or
+merge the pull request, and when the person answers, record their answer
+(`approved_by` or a `*_waiver_approved_by` field set to them, their words in
+`origin.ref` or `approval_ref`) on the same branch and push it to the same pull
+request. Writing down an answer the person gave is not approving it yourself.
+Never open a separate pull request only to carry a signoff, firmness or waiver
+approval.
+
 ## Decision firmness
 
 Requirements and ADRs carry `firmness`, which says what you may do with them.