| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 1 | 1 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 0 | 2 | 0% |
What each file covers
Sections
0 shared · 1 only in A · 1 only in B- − Stop Conditions
- + Agent Rules
Commands
neither file has anySection tags
0 shared · 0 only in A · 2 only in B- + do-not
- + agent-behaviour
Line diff
yxyxy/HordeForge · .clinerules/19_stop_condition.md
@@ −1 @@
1# Stop Conditions
2
3The AI must stop editing when:
4
5- the same change is attempted multiple times
6- tests fail for the same reason repeatedly
7- the same file is edited more than 3 times
8
9In this case the AI must output:
10
11Root cause analysis
12Possible fix
13Required code changes
yxyxy/HordeForge · .clinerules/02_agents.md
@@ +1 @@
1# Agent Rules
2
3Agents are the core units of HordeForge.
4
5Each agent must:
6
7- perform exactly ONE responsibility
8- accept structured context
9- return structured output
10- be deterministic
11- log all decisions
12
13Agent structure:
14
15agents/
16 agent_name/
17 agent.py
18 prompts/
19 schemas.py
20 tests/
21
22All agents must implement:
23
24run(context) -> result
25
26Agents must NOT:
27
28- call other agents directly
29- access external systems directly
30- contain business logic unrelated to their task
31
32Communication between agents occurs only through pipeline context.
@@ −1 +1 @@
1−# Stop Conditions
1+# Agent Rules
22
3−The AI must stop editing when:
3+Agents are the core units of HordeForge.
44
5−- the same change is attempted multiple times
6−- tests fail for the same reason repeatedly
7−- the same file is edited more than 3 times
5+Each agent must:
86
9−In this case the AI must output:
7+- perform exactly ONE responsibility
8+- accept structured context
9+- return structured output
10+- be deterministic
11+- log all decisions
1012
11−Root cause analysis
12−Possible fix
13−Required code changes
13+Agent structure:
14+
15+agents/
16+ agent_name/
17+ agent.py
18+ prompts/
19+ schemas.py
20+ tests/
21+
22+All agents must implement:
23+
24+run(context) -> result
25+
26+Agents must NOT:
27+
28+- call other agents directly
29+- access external systems directly
30+- contain business logic unrelated to their task
31+
32+Communication between agents occurs only through pipeline context.
