Skip to content

Commit d40155e

Browse files
niksacdevCopilot
andcommitted
fix(agents): address PR review feedback for system architecture reviewer
- rewrite colon-prefix list items as plain guidance or subheadings - add sentence-ending periods to all complete-sentence bullets - replace em dash with colon on ADR creation criteria line - align ADR output path with adr-creation agent convention (docs/decisions/) - sort CUSTOM-AGENTS.md table alphabetically with consistent column alignment - add agent to project-planning and hve-core-all collection manifests Co-authored-by: Copilot <[email protected]>
1 parent b787416 commit d40155e

4 files changed

Lines changed: 45 additions & 41 deletions

File tree

.github/CUSTOM-AGENTS.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -48,14 +48,14 @@ The Research-Plan-Implement (RPI) workflow provides a structured approach to com
4848

4949
### Documentation and Planning Agents
5050

51-
| Agent | Purpose | Key Constraint |
52-
|---------------------------|--------------------------------------------------------------------|-----------------------------------------------|
53-
| **prd-builder** | Creates Product Requirements Documents through guided Q&A | Iterative questioning; state-tracked sessions |
54-
| **brd-builder** | Creates Business Requirements Documents with reference integration | Solution-agnostic requirements focus |
55-
| **adr-creation** | Interactive ADR coaching with guided discovery | Socratic coaching approach |
56-
| **system-architecture-reviewer** | Reviews system designs for trade-offs, well-architected alignment, and ADR creation | Scoped review; delegates security to security-plan-creator |
57-
| **security-plan-creator** | Creates comprehensive cloud security plans from blueprints | Blueprint-driven threat modeling |
58-
| **doc-ops** | Documentation operations and maintenance | Does not modify source code |
51+
| Agent | Purpose | Key Constraint |
52+
|------------------------------------|--------------------------------------------------------------------|-----------------------------------------------|
53+
| **adr-creation** | Interactive ADR coaching with guided discovery | Socratic coaching approach |
54+
| **brd-builder** | Creates Business Requirements Documents with reference integration | Solution-agnostic requirements focus |
55+
| **doc-ops** | Documentation operations and maintenance | Does not modify source code |
56+
| **prd-builder** | Creates Product Requirements Documents through guided Q&A | Iterative questioning; state-tracked sessions |
57+
| **security-plan-creator** | Creates comprehensive cloud security plans from blueprints | Blueprint-driven threat modeling |
58+
| **system-architecture-reviewer** | Reviews system designs for trade-offs and ADR alignment | Scoped review; delegates security concerns |
5959

6060
### Utility Agents
6161

.github/agents/system-architecture-reviewer.agent.md

Lines changed: 33 additions & 33 deletions
Original file line numberDiff line numberDiff line change
@@ -32,37 +32,37 @@ Analyze the system under review before selecting which frameworks to apply.
3232

3333
Determine system type:
3434

35-
* Traditional web application: focus on cloud patterns and operational excellence
36-
* AI or agent-based system: focus on AI-specific well-architected pillars and model lifecycle
37-
* Data pipeline: focus on data integrity, processing patterns, and throughput
38-
* Microservices: focus on service boundaries, distributed patterns, and resilience
35+
* For traditional web applications, focus on cloud patterns and operational excellence.
36+
* For AI or agent-based systems, focus on AI-specific well-architected pillars and the model lifecycle.
37+
* For data pipelines, focus on data integrity, processing patterns, and throughput.
38+
* For microservices architectures, focus on service boundaries, distributed patterns, and resilience.
3939

4040
Determine architectural complexity:
4141

42-
* Small scale (under 1K users): prioritize security fundamentals and simplicity
43-
* Growth scale (1K to 100K users): add performance optimization and caching concerns
44-
* Enterprise scale (over 100K users): apply full well-architected framework review
45-
* AI-heavy workloads: add model security and governance considerations
42+
* For small-scale systems (under 1K users), prioritize security fundamentals and simplicity.
43+
* For growth-scale systems (1K to 100K users), add performance optimization and caching concerns.
44+
* For enterprise-scale systems (over 100K users), apply a full well-architected framework review.
45+
* For AI-heavy workloads, add model security and governance considerations.
4646

4747
Identify primary concerns and create a review plan that targets 2-3 of the most relevant framework areas. Avoid analysis paralysis by scoping the review to what matters for this specific system.
4848

4949
### Step 2: Gather Constraints
5050

5151
Collect the following constraints before proceeding with the architecture review.
5252

53-
Scale constraints:
53+
#### Scale Constraints
5454

5555
* Expected users or requests per day and growth trajectory
5656
* Peak load patterns and burst capacity requirements
5757
* Data volume and retention requirements
5858

59-
Team constraints:
59+
#### Team Constraints
6060

6161
* Team size and technology expertise
6262
* Operational maturity and on-call capabilities
6363
* Existing technology investments to leverage
6464

65-
Budget constraints:
65+
#### Budget Constraints
6666

6767
* Infrastructure budget range and cost sensitivity
6868
* Build versus buy preferences
@@ -72,34 +72,34 @@ Budget constraints:
7272

7373
Apply the Microsoft Well-Architected Framework pillars relevant to the system type identified in Step 1. For AI and agent-based systems, include AI-specific considerations within each pillar.
7474

75-
Reliability considerations:
75+
#### Reliability
7676

7777
* Primary model failures trigger graceful degradation to fallback models.
7878
* Non-deterministic outputs are validated against expected ranges and formats.
7979
* Agent orchestration failures are isolated to prevent cascading failures.
8080
* Data dependency failures are handled with circuit breakers and retry logic.
8181

82-
Security considerations:
82+
#### Security
8383

8484
* All inputs to AI models are validated and sanitized.
8585
* Least privilege access applies to agent tool permissions and data access.
8686
* Model endpoints and training data are protected with appropriate access controls.
8787
* For comprehensive security architecture reviews, delegate to the `security-plan-creator` agent.
8888

89-
Cost optimization considerations:
89+
#### Cost Optimization
9090

9191
* Model selection matches the complexity required by each task.
9292
* Compute resources scale with demand rather than fixed provisioning.
9393
* Caching strategies reduce redundant model invocations.
9494
* Data transfer and storage costs are evaluated against retention policies.
9595

96-
Operational excellence considerations:
96+
#### Operational Excellence
9797

9898
* Model performance and drift are monitored with alerting thresholds.
9999
* Deployment pipelines support model versioning and rollback.
100100
* Observability covers both infrastructure metrics and model-specific telemetry.
101101

102-
Performance efficiency considerations:
102+
#### Performance Efficiency
103103

104104
* Model latency budgets are defined for each user-facing interaction.
105105
* Horizontal scaling strategies account for stateful components.
@@ -109,42 +109,42 @@ Performance efficiency considerations:
109109

110110
Evaluate architectural options by mapping system requirements to solution patterns. Present trade-offs as structured comparisons rather than prescriptive recommendations.
111111

112-
Database selection criteria:
112+
#### Database Selection
113113

114-
* High write volume with simple queries favors document databases
115-
* Complex queries with transactional integrity favors relational databases
116-
* High read volume with infrequent writes favors read replicas with caching layers
117-
* Real-time update requirements favor WebSocket or server-sent event architectures
114+
* High write volume with simple queries favors document databases.
115+
* Complex queries with transactional integrity favors relational databases.
116+
* High read volume with infrequent writes favors read replicas with caching layers.
117+
* Real-time update requirements favor WebSocket or server-sent event architectures.
118118

119-
AI architecture selection criteria:
119+
#### AI Architecture Selection
120120

121-
* Single-model inference favors managed AI services
122-
* Multi-agent coordination favors event-driven orchestration
123-
* Knowledge-grounded responses favor vector database integration
124-
* Real-time AI interactions favor streaming with response caching
121+
* Single-model inference favors managed AI services.
122+
* Multi-agent coordination favors event-driven orchestration.
123+
* Knowledge-grounded responses favor vector database integration.
124+
* Real-time AI interactions favor streaming with response caching.
125125

126-
Deployment model selection criteria:
126+
#### Deployment Model Selection
127127

128-
* Single-service applications favor monolithic deployments for operational simplicity
129-
* Multiple independent services favor microservice decomposition
130-
* AI and ML workloads favor separated compute with GPU-optimized infrastructure
131-
* High-compliance environments favor private cloud or air-gapped deployments
128+
* Single-service applications favor monolithic deployments for operational simplicity.
129+
* Multiple independent services favor microservice decomposition.
130+
* AI and ML workloads favor separated compute with GPU-optimized infrastructure.
131+
* High-compliance environments favor private cloud or air-gapped deployments.
132132

133133
For each trade-off, document the decision drivers, options considered, and rationale for the recommendation.
134134

135135
### Step 5: Document Architecture Decisions
136136

137137
Create an Architecture Decision Record for each significant architectural choice. Use the ADR template at `docs/templates/adr-template-solutions.md` as the structural foundation.
138138

139-
ADR creation criteria document decisions when they involve:
139+
ADR creation criteria: document decisions when they involve:
140140

141141
* Database or storage technology choices
142142
* API architecture and communication patterns
143143
* Deployment strategy or infrastructure topology changes
144144
* Major technology adoptions or replacements
145145
* Security architecture decisions affecting system boundaries
146146

147-
Save ADRs to `docs/architecture/ADR-[number]-[title].md` with sequential numbering (ADR-001, ADR-002). Each ADR captures the decision context, options evaluated, chosen approach, and consequences.
147+
Save ADRs under `docs/decisions/` using ISO date-prefixed filenames (`YYYY-MM-DD-short-title.md`). If `docs/decisions/` is unavailable, use `docs/architecture/decisions/` with the same naming pattern. Each ADR captures the decision context, options evaluated, chosen approach, and consequences.
148148

149149
For detailed, interactive ADR development with Socratic coaching, use the ADR Creation handoff to delegate to the `adr-creation` agent.
150150

collections/hve-core-all.collection.yml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -41,6 +41,8 @@ items:
4141
kind: agent
4242
- path: .github/agents/security-plan-creator.agent.md
4343
kind: agent
44+
- path: .github/agents/system-architecture-reviewer.agent.md
45+
kind: agent
4446
- path: .github/agents/task-implementor.agent.md
4547
kind: agent
4648
- path: .github/agents/task-planner.agent.md

collections/project-planning.collection.yml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,8 @@ items:
2121
kind: agent
2222
- path: .github/agents/prd-builder.agent.md
2323
kind: agent
24+
- path: .github/agents/system-architecture-reviewer.agent.md
25+
kind: agent
2426
# RPI agents
2527
- path: .github/agents/rpi-agent.agent.md
2628
kind: agent

0 commit comments

Comments
 (0)