spec-ctx 0.1.0 → 0.1.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "spec-ctx",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "description": "Deterministic context engine and task workflow for OpenSpec projects.",
   "type": "module",
   "license": "MIT",

package/schemas/spec-driven-ids/README.md

@@ -5,14 +5,27 @@ A fork of the OpenSpec `spec-driven` schema. It adds stable IDs from spec-ctx to
 - The spec template starts each requirement with `REQ-<CAP>-NNN` and each scenario with `SCN-<CAP>-NNN-<n>`.
 - The instructions tell the agent to get IDs from `specctx id new` and to link IDs with `Refs:` lines.
 - The tasks template cites REQ IDs and puts the `Verify:` command in a code span, so `specctx task done` can run it.
-- `config-fragment.yaml` holds the `rules` and `operations` that `specctx init --schema` adds to `openspec/config.yaml`.
+- `config-fragment.yaml` holds the `rules` and `operations` for `openspec/config.yaml`.
 
-Forked from OpenSpec 1.14.3 with `openspec schema fork spec-driven spec-driven-ids`. CI validates it against that version.
+## Install by copy
+
+- Clone the repository: `git clone https://github.com/sonqh/spec-ctx`.
+- Copy `schemas/spec-driven-ids` to `openspec/schemas/spec-driven-ids` in your project.
+- Set `schema: spec-driven-ids` in `openspec/config.yaml`.
+- Merge `config-fragment.yaml` into `openspec/config.yaml` by hand. Add its `rules` and `operations` keys. Keep every item quoted.
+- Run `openspec schema validate spec-driven-ids`.
 
-## Install
+## Install with init --schema
 
 ```bash
-npx spec-ctx init --schema
+npx -y spec-ctx init --schema
 ```
 
-The command copies this folder to `openspec/schemas/spec-driven-ids/` and sets `schema: spec-driven-ids` in `openspec/config.yaml`.
+- The command copies this folder to `openspec/schemas/spec-driven-ids/`.
+- It sets `schema: spec-driven-ids` in `openspec/config.yaml`.
+- It adds the `rules` and `operations` keys that the config does not have yet. It leaves other keys as they are.
+- It quotes a list item that YAML would read as a mapping.
+
+## Version
+
+Forked from OpenSpec 1.14.3 with `openspec schema fork spec-driven spec-driven-ids`. CI validates it against that version.

package/schemas/spec-driven-ids/config-fragment.yaml

@@ -2,24 +2,24 @@
 # that the project config does not have yet. It never changes a key that exists.
 rules:
   specs:
-    - Every requirement header starts with its ID, e.g. "### Requirement: REQ-ABC-001 Name". Get the ID from `specctx id new REQ ABC`.
-    - Every scenario header starts with its ID, e.g. "#### Scenario: SCN-ABC-001-1 Name".
-    - A requirement may end with a line "Refs: REQ-ABC-002, ADR-001" to link related IDs.
-    - Requirement text stays under 500 characters. Move detail into scenarios.
+    - 'Every requirement header starts with its ID, e.g. "### Requirement: REQ-ABC-001 Name". Get the ID from `specctx id new REQ ABC`.'
+    - 'Every scenario header starts with its ID, e.g. "#### Scenario: SCN-ABC-001-1 Name".'
+    - 'A requirement may end with a line "Refs: REQ-ABC-002, ADR-001" to link related IDs.'
+    - 'Requirement text stays under 500 characters. Move detail into scenarios.'
   design:
-    - Each decision is one bullet under "## Decisions". Add new decisions at the end.
+    - 'Each decision is one bullet under "## Decisions". Add new decisions at the end.'
   tasks:
-    - Every task cites at least one REQ ID in square brackets, e.g. "[REQ-ABC-001]".
-    - Every task states its verification as a command in a code span after "Verify:".
+    - 'Every task cites at least one REQ ID in square brackets, e.g. "[REQ-ABC-001]".'
+    - 'Every task states its verification as a command in a code span after "Verify:".'
 
 operations:
   apply:
     guidance:
-      - Start each task with `specctx task start <id>` and read the bundle it prints before you read specs.
-      - Tag code with the REQ ID it implements (a comment `// REQ-ABC-001`). Tag tests with `// Covers: REQ-ABC-001`.
-      - Close each task with `specctx task done <id>`. Never tick a checkbox by hand.
-      - Run `specctx check --strict` after each task group.
+      - 'Start each task with `specctx task start <id>` and read the bundle it prints before you read specs.'
+      - 'Tag code with the REQ ID it implements (a comment `// REQ-ABC-001`). Tag tests with `// Covers: REQ-ABC-001`.'
+      - 'Close each task with `specctx task done <id>`. Never tick a checkbox by hand.'
+      - 'Run `specctx check --strict` after each task group.'
   archive:
     guidance:
-      - Run `specctx check --strict` and `openspec validate --all --strict`. Both must pass before archive.
-      - Run `openspec validate --all --strict` again after archive and before push.
+      - 'Run `specctx check --strict` and `openspec validate --all --strict`. Both must pass before archive.'
+      - 'Run `openspec validate --all --strict` again after archive and before push.'

package/skills/specctx-done/SKILL.md

@@ -11,7 +11,7 @@ Close the current task with evidence. Run `specctx` as `npx spec-ctx` when it is
 
 1. Run `specctx task done <task>`. It runs the `Verify:` command of the task in the project root.
 2. On exit 0 it writes `.ctx/evidence/<change>/<task>.json` and sets `[x]` on the task line. Nothing else in `tasks.md` changes.
-3. On a failure it prints the last 20 lines of output and exits 1. The task stays open. Fix the cause and run step 1 again.
+3. On a failure it prints the last 20 lines of output and then the line `Verify failed (exit <n>). The task stays open.` It exits 1. Fix the cause and run step 1 again.
 4. If the task has prose after `Verify:` and no command, run `specctx task done <task> --manual "<what you checked>"`.
 5. After the last task of a group, run `specctx check --strict`. Fix every finding before the next group.
 6. Run `specctx handoff write`. It writes `.ctx/handoff.md` from the index, the evidence, and the open questions.