pi-diffwarden 0.26.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +755 -0
- package/LICENSE +21 -0
- package/README.md +846 -0
- package/extensions/diffwarden/index.ts +84 -0
- package/package.json +31 -0
- package/skills/diffwarden/SKILL.md +2428 -0
- package/skills/diffwarden/commands/diffwarden.md +22 -0
- package/skills/diffwarden/commands/dw.md +22 -0
- package/skills/diffwarden/prompts/diffwarden.md +3 -0
- package/skills/diffwarden/prompts/dw.md +3 -0
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
# Diffwarden
|
|
2
|
+
|
|
3
|
+
Read and follow the **diffwarden** skill (`SKILL.md`).
|
|
4
|
+
|
|
5
|
+
The user text after this command (if any) is a Diffwarden invocation. Parse per the skill **Slash Commands** section:
|
|
6
|
+
|
|
7
|
+
- No args → `help`
|
|
8
|
+
- Else parse subcommand (`review`, `loop`, `status`, `comment`, `help`), an optional target, and flags
|
|
9
|
+
- Primary subcommands: `review` (read-only), `loop` (review-fix-verify until c5/5), `status` (score only), `comment` (short PR review comment), `help`
|
|
10
|
+
- Compatibility aliases (accept, don't advertise): `fix` → `loop`; `prepare` → `loop --push`; `security` → `review --security`; `review-plan <file>` → `review <file> --as-plan`; `fix-plan <file>` → `loop <file> --as-plan`
|
|
11
|
+
- Targets: `workspace` (current folder, git not required), `local` (git working tree), `staged` (git staged), PR (`#123`, URL), or file path (plan/docs/guides/tutorials)
|
|
12
|
+
- Flags: `--mvp`, `--verbose`, `--orchestrate`, `--commit`, `--push`, `--as-code`, `--as-plan`, `--web` (alias `--research`), `--reply`, `--resolve`, `--delegate`, `--dry-run`, `--max N`, `--review-model`, `--fix-code-model`, `--fix-text-model`, `--security`
|
|
13
|
+
- `review`/`loop` auto-detect code vs document mode per skill **Target Auto-Detection**; `--as-code`/`--as-plan` override. `comment` is PR-only.
|
|
14
|
+
- `--web` is opt-in per-finding consent; valid on `review`/`loop` (code targets); rejected on `status` and document mode.
|
|
15
|
+
- `--orchestrate` enables optional reviewer/fixer role split; off by default. Model flags override config when set.
|
|
16
|
+
- Default output is lean (`cN/5` loop lines plus final `Status:`/`Level:` lines); `--verbose` restores full report.
|
|
17
|
+
|
|
18
|
+
Examples: `loop workspace`, `review #123`, `comment #123`, `status local`, `loop docs/install.md --as-plan`, `review --security`, `loop --orchestrate`, `loop --mvp`, `review #123 --web`.
|
|
19
|
+
|
|
20
|
+
If the `caveman` skill is loaded, run in caveman mode — see the skill **Caveman Mode** section.
|
|
21
|
+
|
|
22
|
+
Expand to skill flags, run full Diffwarden loop. Do not rephrase unless parse fails.
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
# Diffwarden (`/dw`)
|
|
2
|
+
|
|
3
|
+
Read and follow the **diffwarden** skill (`SKILL.md`).
|
|
4
|
+
|
|
5
|
+
The user text after this command (if any) is a Diffwarden invocation. Parse per the skill **Slash Commands** section:
|
|
6
|
+
|
|
7
|
+
- No args → `help`
|
|
8
|
+
- Else parse subcommand (`review`, `loop`, `status`, `comment`, `help`), an optional target, and flags
|
|
9
|
+
- Primary subcommands: `review` (read-only), `loop` (review-fix-verify until c5/5), `status` (score only), `comment` (short PR review comment), `help`
|
|
10
|
+
- Compatibility aliases (accept, don't advertise): `fix` → `loop`; `prepare` → `loop --push`; `security` → `review --security`; `review-plan <file>` → `review <file> --as-plan`; `fix-plan <file>` → `loop <file> --as-plan`
|
|
11
|
+
- Targets: `workspace` (current folder, git not required), `local` (git working tree), `staged` (git staged), PR (`#123`, URL), or file path (plan/docs/guides/tutorials)
|
|
12
|
+
- Flags: `--mvp`, `--verbose`, `--orchestrate`, `--commit`, `--push`, `--as-code`, `--as-plan`, `--web` (alias `--research`), `--reply`, `--resolve`, `--delegate`, `--dry-run`, `--max N`, `--review-model`, `--fix-code-model`, `--fix-text-model`, `--security`
|
|
13
|
+
- `review`/`loop` auto-detect code vs document mode per skill **Target Auto-Detection**; `--as-code`/`--as-plan` override. `comment` is PR-only.
|
|
14
|
+
- `--web` is opt-in per-finding consent; valid on `review`/`loop` (code targets); rejected on `status` and document mode.
|
|
15
|
+
- `--orchestrate` enables optional reviewer/fixer role split; off by default. Model flags override config when set.
|
|
16
|
+
- Default output is lean (`cN/5` loop lines plus final `Status:`/`Level:` lines); `--verbose` restores full report.
|
|
17
|
+
|
|
18
|
+
Examples: `loop workspace`, `review #123`, `comment #123`, `status local`, `loop docs/install.md --as-plan`, `review --security`, `loop --orchestrate`, `loop --mvp`, `review #123 --web`.
|
|
19
|
+
|
|
20
|
+
If the `caveman` skill is loaded, run in caveman mode — see the skill **Caveman Mode** section.
|
|
21
|
+
|
|
22
|
+
Expand to skill flags, run full Diffwarden loop. Do not rephrase unless parse fails.
|