great-cto 1.0.168 → 1.0.169
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/dist/bootstrap.js +12 -0
- package/package.json +1 -1
package/dist/bootstrap.js
CHANGED
|
@@ -59,6 +59,18 @@ compliance: [${complianceLine}]
|
|
|
59
59
|
> \`compliance:\` list drives which checklists security-officer runs.
|
|
60
60
|
> See ARCHETYPES.md "Parameter Values" for supported keys.
|
|
61
61
|
|
|
62
|
+
## Memory & Query Rule
|
|
63
|
+
|
|
64
|
+
> Before reading source files, agents should query memory layers in this order:
|
|
65
|
+
> 1. **\`.great_cto/lessons.md\`** — project-specific lessons learned
|
|
66
|
+
> 2. **\`~/.great_cto/decisions.md\`** — global decisions log (ADR-style, all projects)
|
|
67
|
+
> 3. **\`~/.great_cto/verdicts/\`** — past agent verdicts (APPROVED/BLOCKED with rationale)
|
|
68
|
+
> 4. Only then read source files for the actual implementation
|
|
69
|
+
>
|
|
70
|
+
> This prevents re-deriving solved problems and surfaces "we decided this last
|
|
71
|
+
> sprint" insights. Agents update these layers via gate approvals (auto) and
|
|
72
|
+
> by appending to \`lessons.md\` after retrospectives.
|
|
73
|
+
|
|
62
74
|
## Goals
|
|
63
75
|
|
|
64
76
|
- <add your primary goal here>
|
package/package.json
CHANGED