planr 1.10.0-alpha.4 → 1.10.0-alpha.5
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/npm/native/darwin-arm64/planr +0 -0
- package/npm/native/darwin-arm64/planr-host-capability-validator +0 -0
- package/npm/native/darwin-x86_64/planr +0 -0
- package/npm/native/darwin-x86_64/planr-host-capability-validator +0 -0
- package/npm/native/linux-arm64/planr +0 -0
- package/npm/native/linux-arm64/planr-host-capability-validator +0 -0
- package/npm/native/linux-x86_64/planr +0 -0
- package/npm/native/linux-x86_64/planr-host-capability-validator +0 -0
- package/package.json +1 -1
- package/plugins/planr/.claude-plugin/plugin.json +1 -1
- package/plugins/planr/.codex-plugin/plugin.json +1 -1
- package/plugins/planr/skills/planr/SKILL.md +2 -1
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "planr",
|
|
3
3
|
"description": "Skill-driven planning and execution loop for coding agents: one planr entry point, an autonomous planr-loop, and evidence-backed task graph skills powered by the planr CLI.",
|
|
4
|
-
"version": "1.10.0-alpha.
|
|
4
|
+
"version": "1.10.0-alpha.5",
|
|
5
5
|
"author": {
|
|
6
6
|
"name": "instructa"
|
|
7
7
|
},
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "planr",
|
|
3
|
-
"version": "1.10.0-alpha.
|
|
3
|
+
"version": "1.10.0-alpha.5",
|
|
4
4
|
"description": "Skill-driven planning and execution loop for coding agents: one $planr entry point, an autonomous $planr-loop, and evidence-backed task graph skills powered by the planr CLI.",
|
|
5
5
|
"author": {
|
|
6
6
|
"name": "instructa",
|
|
@@ -38,8 +38,8 @@ Evaluate top to bottom; pick the first row that matches both intent and state:
|
|
|
38
38
|
|
|
39
39
|
| Intent | State condition | Route |
|
|
40
40
|
| --- | --- | --- |
|
|
41
|
-
| "set up a goal", "prepare a /goal run", broad long-running goal not yet planned | no plan or contract for that scope | `planr-goal` (prep only, prints the loop starter) |
|
|
42
41
|
| "build until done", "loop", "finish this feature autonomously" | any | `planr-loop` |
|
|
42
|
+
| "set up a goal", "prepare a /goal run", or another explicitly prep-only goal request | no plan or contract for that scope | `planr-goal` (prep only, prints the loop starter) |
|
|
43
43
|
| status, "what's left", "what's blocked" | any | `planr-status` |
|
|
44
44
|
| summary of completed scope | any | `planr-summary` |
|
|
45
45
|
| new idea, PRD, scope, architecture | no plan, or plan needs refinement | `planr-plan` |
|
|
@@ -53,6 +53,7 @@ Evaluate top to bottom; pick the first row that matches both intent and state:
|
|
|
53
53
|
## Rules
|
|
54
54
|
|
|
55
55
|
- Route to exactly one skill per dispatch. If the request spans stages (idea -> running feature), route to `planr-loop` and let the loop sequence the stages.
|
|
56
|
+
- Explicit delivery language such as "implement", "work autonomously until complete", or "finish this" outranks missing plan or map state and routes to `planr-loop`. Never turn a delivery request into a prep-only handoff.
|
|
56
57
|
- Never skip a stage: no map items without a checked build plan, no FeatureRun completion without its required ReviewGates, and no review verdict without evidence.
|
|
57
58
|
- When delegating to a subagent, prompt it with a skill reference plus item id (for example: `Use $planr-work on item <id>`), never with a hand-written workflow prompt.
|
|
58
59
|
- The maker never reviews its own work. Reviews run through `planr-review` in a separate agent or subagent whenever the host supports it.
|