@chorus-aidlc/chorus-openclaw-plugin 0.17.1 → 0.17.2
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/package.json +1 -1
- package/skills/brainstorm/SKILL.md +1 -1
- package/skills/chorus/SKILL.md +2 -2
- package/skills/chorus-cli/SKILL.md +11 -1
- package/skills/code-reviewer/SKILL.md +1 -1
- package/skills/develop/SKILL.md +2 -2
- package/skills/docs/SKILL.md +1 -1
- package/skills/idea/SKILL.md +1 -1
- package/skills/openspec-aware/SKILL.md +1 -1
- package/skills/orchestrate/SKILL.md +1 -1
- package/skills/proposal/SKILL.md +1 -1
- package/skills/proposal-reviewer/SKILL.md +1 -1
- package/skills/quick-dev/SKILL.md +1 -1
- package/skills/review/SKILL.md +1 -1
- package/skills/task-reviewer/SKILL.md +1 -1
- package/skills/yolo/SKILL.md +3 -3
package/package.json
CHANGED
package/skills/chorus/SKILL.md
CHANGED
|
@@ -4,7 +4,7 @@ description: Chorus AI Agent collaboration platform — overview, common tools,
|
|
|
4
4
|
license: AGPL-3.0
|
|
5
5
|
metadata:
|
|
6
6
|
author: chorus
|
|
7
|
-
version: "0.17.
|
|
7
|
+
version: "0.17.2"
|
|
8
8
|
category: project-management
|
|
9
9
|
mcp_server: chorus
|
|
10
10
|
---
|
|
@@ -130,7 +130,7 @@ Projects can be organized into **Project Groups** — a single-level grouping th
|
|
|
130
130
|
|
|
131
131
|
### Reports
|
|
132
132
|
|
|
133
|
-
A **report** is a short idea-completion summary persisted as a `type="report"` Document at end-of-Idea, authored via `chorus_create_report` (gated on `document:write`). The `content`
|
|
133
|
+
A **report** is a short idea-completion summary persisted as a `type="report"` Document at end-of-Idea, authored via `chorus_create_report` (gated on `document:write`). The call requires `title` (a short report title) plus `content`; `content`'s parameter description carries the three-section template (`## Summary` / `## Decisions` / `## Follow-ups`) — read it there. `/yolo` writes one mandatorily; `/develop` offers it advisorily on last-task verify.
|
|
134
134
|
|
|
135
135
|
### References
|
|
136
136
|
|
|
@@ -4,7 +4,7 @@ description: How to install, configure, and use the `chorus` CLI — install it,
|
|
|
4
4
|
license: AGPL-3.0
|
|
5
5
|
metadata:
|
|
6
6
|
author: chorus
|
|
7
|
-
version: "0.17.
|
|
7
|
+
version: "0.17.2"
|
|
8
8
|
category: project-management
|
|
9
9
|
mcp_server: chorus
|
|
10
10
|
---
|
|
@@ -35,6 +35,16 @@ Agent configuration lives in `~/.chorus/daemon.json`; `chorus agents` is the CRU
|
|
|
35
35
|
- `chorus agents remove <name|uuid>` — remove a configured agent from `~/.chorus/daemon.json`
|
|
36
36
|
(matched by UUID or name; an ambiguous name → use the UUID).
|
|
37
37
|
|
|
38
|
+
- `chorus agents run --name <name|uuid> [--type <type>] [--] [agent args…]` — launch a
|
|
39
|
+
configured agent's binary in the FOREGROUND with its Chorus connection injected into the
|
|
40
|
+
child only (`CHORUS_URL` / `CHORUS_API_KEY` / `CHORUS_AGENT_PROFILE`; nothing is exported to
|
|
41
|
+
the parent shell, and the key is never printed). Agent selection: single agent by default; else `--name`, else `CHORUS_AGENT_PROFILE`; ambiguous/none →
|
|
42
|
+
error. Backend defaults to the agent's stored `agentType`, overridable with `--type`.
|
|
43
|
+
Everything after `--` is passed to the agent **verbatim** (never inspected). Type → binary:
|
|
44
|
+
`claude-code`/`claude`→`claude`, `codex`→`codex`, `kiro`→`kiro-cli`, `pi`→`pi`,
|
|
45
|
+
`opencode`→`opencode`, `openclaw`→`openclaw`, `dsh`→`dsh-jsonrpc-agent`. Agents added as
|
|
46
|
+
opencode/openclaw/dsh are stored as `offline` → pass `--type` explicitly to launch them.
|
|
47
|
+
|
|
38
48
|
## 3. Connection environment variables
|
|
39
49
|
|
|
40
50
|
- `CHORUS_URL` — the Chorus instance URL.
|
package/skills/develop/SKILL.md
CHANGED
|
@@ -4,7 +4,7 @@ description: Chorus Development workflow — claim tasks, report work, manage se
|
|
|
4
4
|
license: AGPL-3.0
|
|
5
5
|
metadata:
|
|
6
6
|
author: chorus
|
|
7
|
-
version: "0.17.
|
|
7
|
+
version: "0.17.2"
|
|
8
8
|
category: project-management
|
|
9
9
|
mcp_server: chorus
|
|
10
10
|
---
|
|
@@ -279,7 +279,7 @@ Once Admin verifies (status: `done`), move to the next available task (back to S
|
|
|
279
279
|
|
|
280
280
|
### Step 11: Idea Completion Report (advisory)
|
|
281
281
|
|
|
282
|
-
If the task you just self-verified was the LAST one of its Idea (every Task across every approved Proposal is now `done`/`closed`) and you have `document:write`, offer to call `chorus_create_report`. On OpenClaw, ask the user as a plain-text prompt (e.g. "This was the last task of the idea. Want me to write a completion report? Reply yes/no.") — there is no `AskUserQuestion` primitive. The `content`
|
|
282
|
+
If the task you just self-verified was the LAST one of its Idea (every Task across every approved Proposal is now `done`/`closed`) and you have `document:write`, offer to call `chorus_create_report`. On OpenClaw, ask the user as a plain-text prompt (e.g. "This was the last task of the idea. Want me to write a completion report? Reply yes/no.") — there is no `AskUserQuestion` primitive. The call requires `title` (a short report title) plus `content`; `content`'s parameter description carries the three-section template (`## Summary` / `## Decisions` / `## Follow-ups`). Skip on decline.
|
|
283
283
|
|
|
284
284
|
---
|
|
285
285
|
|
package/skills/docs/SKILL.md
CHANGED
package/skills/idea/SKILL.md
CHANGED
package/skills/proposal/SKILL.md
CHANGED
package/skills/review/SKILL.md
CHANGED
package/skills/yolo/SKILL.md
CHANGED
|
@@ -4,7 +4,7 @@ description: Full-auto AI-DLC pipeline — from prompt to done. Automates the en
|
|
|
4
4
|
license: AGPL-3.0
|
|
5
5
|
metadata:
|
|
6
6
|
author: chorus
|
|
7
|
-
version: "0.17.
|
|
7
|
+
version: "0.17.2"
|
|
8
8
|
category: project-management
|
|
9
9
|
mcp_server: chorus
|
|
10
10
|
---
|
|
@@ -159,7 +159,7 @@ In /yolo mode, the agent generates elaboration questions and answers them itself
|
|
|
159
159
|
{ id: "b", label: "<option B>" }
|
|
160
160
|
]
|
|
161
161
|
}
|
|
162
|
-
// ... 5-8 questions covering functional,
|
|
162
|
+
// ... 5-8 questions covering functional, technical_context, scope aspects
|
|
163
163
|
]
|
|
164
164
|
})
|
|
165
165
|
```
|
|
@@ -485,7 +485,7 @@ After all waves complete, output a markdown summary:
|
|
|
485
485
|
|
|
486
486
|
### Phase 5b: Idea Completion Report (mandatory)
|
|
487
487
|
|
|
488
|
-
A successful `/yolo` run always finishes the Idea — call `chorus_create_report` once with `proposalUuid` set to the last verified proposal. The `content`
|
|
488
|
+
A successful `/yolo` run always finishes the Idea — call `chorus_create_report` once with `proposalUuid` set to the last verified proposal. The call requires `title` (a short report title) plus `content`; `content`'s parameter description carries the three-section template (`## Summary` / `## Decisions` / `## Follow-ups`); follow it. Surface the returned `documentUuid` in the Phase 5 summary. Skipping is a protocol violation.
|
|
489
489
|
|
|
490
490
|
> **Order:** write the completion report only **after** the Phase 4.5 code-review gateway returns PASS / PASS WITH NOTES — never while a code-review FAIL is outstanding.
|
|
491
491
|
|