RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Configs/yxyxy/HordeForge/diff

Two files, one repository

yxyxy/HordeForge ships 2 formats across 16 indexed files. The question worth asking is whether the second one says anything the first does not.

CompareAGENTS.md ↔ Cline rules
A · AGENTS.md · 576 wordsB · .clinerules/04_testing.md · 76 words
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections01320%
Commands0400%
Section tags34043%

What each file covers

Sections

0 shared · 13 only in A · 2 only in B
  • − AGENTS.md
  • − Project Overview
  • − Architecture Rules
  • − Agent Rules
  • − Code Rules
  • − Edit Rules
  • − Testing Workflow (MANDATORY)
  • − Refactoring Rules
  • − Pipeline Rules
  • − Safety Rules
  • − Failure & Stop Conditions
  • − Loop Prevention
  • − Expected Behavior
  • + Testing Rules
  • + Test Execution

Commands

0 shared · 4 only in A · 0 only in B
  • − ruff
  • − ruff check --fix
  • − ruff format
  • − pytest -v --tb=short

Section tags

3 shared · 4 only in A · 0 only in B
  • − code-style
  • − architecture
  • − deployment
  • − agent-behaviour
  •   test
  •   lint-format
  •   do-not

Line diff

+22 added−134 removed15 unchanged10.1% identical
yxyxy/HordeForge · AGENTS.md
@@ −1 @@
1# AGENTS.md
2 
3## Project Overview
4 
5HordeForge is an AI-first, agent-driven system for building, testing, and deploying code through deterministic pipelines.
6 
7Core principles:
8- AI Pipeline > Integrations > Platform
9- Deterministic execution over “smart” behavior
10- Simplicity over abstraction
11- Minimal infrastructure unless required
12 
13---
14 
15## Architecture Rules
16 
17- The system is agent-driven: logic is implemented via agents, not services
18- Each agent has a single responsibility
19- No hidden side effects between components
20- Avoid unnecessary layers, abstractions, or frameworks
21- Prefer explicit data flow over implicit coupling
22 
23---
24 
25## Agent Rules
26 
27- One agent = one responsibility
28- Agents must use structured input and structured output
29- No direct agent-to-agent calls (use orchestrator/pipeline)
30- Agents must be deterministic and reproducible
31- All important steps must be logged
32- Avoid hidden state and implicit context
33 
34---
35 
36## Code Rules
37 
38- Language: Python 3.11+
39- All functions must have type hints
40- Prefer `dataclasses` over plain classes
41- Use `pydantic` for validation and schemas
42- No global mutable state
43- Max file size: ~500 lines (split if larger)
44 
45Code style:
46- Follow `ruff` rules
47- Keep functions small and focused
48- Avoid duplication
49- Prefer readability over cleverness
50 
51---
52 
53## Edit Rules
54 
55- Always search for existing implementation before adding new code
56- Prefer editing existing files over creating new ones
57- Make the smallest possible change to solve the task
58- Do not rewrite entire files unless absolutely necessary
59- Do not duplicate functionality
60- Preserve existing architecture and patterns
61 
62Before major edits:
63- Understand the relevant part of the codebase
64- Identify impacted files
65- Keep changes localized
66 
67---
68 
69## Testing Workflow (MANDATORY)
70 
71- Tests must be written or updated before implementation (TDD)
72- After code changes:
73 1. Run `ruff check --fix`
74 2. Run `ruff format`
75 3. Run `pytest -v --tb=short` (only if tests exist for edited code)
76 
77Rules:
78- All tests must pass before task is considered complete
79- Do not skip or disable tests
80- Do not change tests to make failures disappear without fixing root cause
81 
82---
83 
84## Refactoring Rules
85 
86- Refactoring only allowed when tests exist
87- Must not change behavior
88- No mixing refactoring with new features
89- Keep changes incremental and verifiable
90 
91---
92 
93## Pipeline Rules
94 
95- Work follows deterministic pipeline:
96 1. Analyze
97 2. Plan
98 3. Test
99 4. Implement
100 5. Validate
101 
102- Do not skip steps
103- Do not jump directly to coding without understanding context
104 
105---
106 
107## Safety Rules
108 
109- Do not modify unrelated files
110- Do not delete files unless explicitly required
111- No destructive git operations:
112 - no force push
113 - no history rewrite
114- Do not introduce breaking changes without clear reason
115 
116---
117 
118## Failure & Stop Conditions
119 
120- Maximum 3 attempts to fix the same issue
121- Do not repeat the same fix strategy
122- If the same error persists:
123 - Stop
124 - Analyze root cause
125 - Output diagnosis instead of continuing blindly
126 
127Stop immediately if:
128- Errors repeat without progress
129- Required context is missing
130- The change would break architecture or safety rules
131 
132---
133 
134## Loop Prevention
135 
136- Do not repeat identical edits
137- Do not re-run the same failing approach
138- Always change strategy after a failed attempt
139- Prefer analysis over blind retries
140 
141---
142 
143## Expected Behavior
144 
145- Be precise and minimal
146- Prefer correct over clever
147- Explain reasoning when making non-trivial changes
148- Keep output structured and actionable
149- When blocked — stop and explain, not guess
yxyxy/HordeForge · .clinerules/04_testing.md
@@ +1 @@
1# Testing Rules
2 
3HordeForge follows strict TDD.
4 
5Order:
6 
71. BDD scenarios
82. Test generation
93. Code generation
 
 
10 
11Tests must exist before code.
12 
13Test types:
14 
15tests/
16 unit/
17 integration/
18 pipeline/
 
19 
20Coverage target:
21 
22> 80%
23 
24Agents must always have unit tests.
 
 
 
 
 
25 
26The system must support automated test execution in sandbox environments.
27 
28## Test Execution
29 
30Tests must be executed using:
 
 
 
 
 
31 
32pytest -v --tb=short
 
 
 
 
33 
34The test runner must only run after the Ruff auto-fix step:
35 
36ruff check --fix
37pytest -v --tb=short
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
@@ −1 +1 @@
1−# AGENTS.md
1+# Testing Rules
22  
3−## Project Overview
3+HordeForge follows strict TDD.
44  
5−HordeForge is an AI-first, agent-driven system for building, testing, and deploying code through deterministic pipelines.
5+Order:
66  
7−Core principles:
8−- AI Pipeline > Integrations > Platform
9−- Deterministic execution over “smart” behavior
10−- Simplicity over abstraction
11−- Minimal infrastructure unless required
7+1. BDD scenarios
8+2. Test generation
9+3. Code generation
1210  
13−---
11+Tests must exist before code.
1412  
15−## Architecture Rules
13+Test types:
1614  
17−- The system is agent-driven: logic is implemented via agents, not services
18−- Each agent has a single responsibility
19−- No hidden side effects between components
20−- Avoid unnecessary layers, abstractions, or frameworks
21−- Prefer explicit data flow over implicit coupling
15+tests/
16+ unit/
17+ integration/
18+ pipeline/
2219  
23−---
20+Coverage target:
2421  
25−## Agent Rules
22+> 80%
2623  
27−- One agent = one responsibility
28−- Agents must use structured input and structured output
29−- No direct agent-to-agent calls (use orchestrator/pipeline)
30−- Agents must be deterministic and reproducible
31−- All important steps must be logged
32−- Avoid hidden state and implicit context
24+Agents must always have unit tests.
3325  
34−---
26+The system must support automated test execution in sandbox environments.
3527  
36−## Code Rules
28+## Test Execution
3729  
38−- Language: Python 3.11+
39−- All functions must have type hints
40−- Prefer `dataclasses` over plain classes
41−- Use `pydantic` for validation and schemas
42−- No global mutable state
43−- Max file size: ~500 lines (split if larger)
30+Tests must be executed using:
4431  
45−Code style:
46−- Follow `ruff` rules
47−- Keep functions small and focused
48−- Avoid duplication
49−- Prefer readability over cleverness
32+pytest -v --tb=short
5033  
51−---
34+The test runner must only run after the Ruff auto-fix step:
5235  
53−## Edit Rules
54− 
55−- Always search for existing implementation before adding new code
56−- Prefer editing existing files over creating new ones
57−- Make the smallest possible change to solve the task
58−- Do not rewrite entire files unless absolutely necessary
59−- Do not duplicate functionality
60−- Preserve existing architecture and patterns
61− 
62−Before major edits:
63−- Understand the relevant part of the codebase
64−- Identify impacted files
65−- Keep changes localized
66− 
67−---
68− 
69−## Testing Workflow (MANDATORY)
70− 
71−- Tests must be written or updated before implementation (TDD)
72−- After code changes:
73− 1. Run `ruff check --fix`
74− 2. Run `ruff format`
75− 3. Run `pytest -v --tb=short` (only if tests exist for edited code)
76− 
77−Rules:
78−- All tests must pass before task is considered complete
79−- Do not skip or disable tests
80−- Do not change tests to make failures disappear without fixing root cause
81− 
82−---
83− 
84−## Refactoring Rules
85− 
86−- Refactoring only allowed when tests exist
87−- Must not change behavior
88−- No mixing refactoring with new features
89−- Keep changes incremental and verifiable
90− 
91−---
92− 
93−## Pipeline Rules
94− 
95−- Work follows deterministic pipeline:
96− 1. Analyze
97− 2. Plan
98− 3. Test
99− 4. Implement
100− 5. Validate
101− 
102−- Do not skip steps
103−- Do not jump directly to coding without understanding context
104− 
105−---
106− 
107−## Safety Rules
108− 
109−- Do not modify unrelated files
110−- Do not delete files unless explicitly required
111−- No destructive git operations:
112− - no force push
113− - no history rewrite
114−- Do not introduce breaking changes without clear reason
115− 
116−---
117− 
118−## Failure & Stop Conditions
119− 
120−- Maximum 3 attempts to fix the same issue
121−- Do not repeat the same fix strategy
122−- If the same error persists:
123− - Stop
124− - Analyze root cause
125− - Output diagnosis instead of continuing blindly
126− 
127−Stop immediately if:
128−- Errors repeat without progress
129−- Required context is missing
130−- The change would break architecture or safety rules
131− 
132−---
133− 
134−## Loop Prevention
135− 
136−- Do not repeat identical edits
137−- Do not re-run the same failing approach
138−- Always change strategy after a failed attempt
139−- Prefer analysis over blind retries
140− 
141−---
142− 
143−## Expected Behavior
144− 
145−- Be precise and minimal
146−- Prefer correct over clever
147−- Explain reasoning when making non-trivial changes
148−- Keep output structured and actionable
149−- When blocked — stop and explain, not guess
36+ruff check --fix
37+pytest -v --tb=short

Also from Kynth Studios

Built for the same person as RuleStack

ToolDrift

What the AI coding tools changed last night

tooldrift.kynth.studio

StillShipping

Which agent tools have stopped shipping

stillshipping.kynth.studio

BlockDex

Search inside every shadcn registry

blockdex.kynth.studio

The studio list

One product, taken apart, once a month

Kynth Studios pulls one shipped product open every month — what it does, what it cost to build, what the pipeline behind it looks like, and what the numbers did. One email a month, nothing in between.

Double opt-in — we send one confirmation link and nothing else until you click it.

RuleStack

Built by

Kynth Studios

the studio behind ToolDrift, StillShipping and BlockDex

part of Toolproof, the measurement layer for AI agent tooling

Directory

Configs
Stacks
Compare formats
AGENTS.md vs CLAUDE.md
Cursor rules alternatives
Diff two configs
Best AGENTS.md examples
Best Cursor rules examples
What goes in a CLAUDE.md

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

© 2026 RuleStack. A Kynth Studios product. Changelog

RuleStack

The studio list

One product, taken apart, once a month

Kynth Studios pulls one shipped product open every month — what it does, what it cost to build, what the pipeline behind it looks like, and what the numbers did. One email a month, nothing in between.

Double opt-in — we send one confirmation link and nothing else until you click it.

RuleStack

Built by

Kynth Studios

the studio behind ToolDrift, StillShipping and BlockDex

part of Toolproof, the measurement layer for AI agent tooling

Directory

Configs
Stacks
Compare formats
AGENTS.md vs CLAUDE.md
Cursor rules alternatives
Diff two configs
Best AGENTS.md examples
Best Cursor rules examples
What goes in a CLAUDE.md

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

© 2026 RuleStack. A Kynth Studios product. Changelog

RuleStack

The studio list

One product, taken apart, once a month

Kynth Studios pulls one shipped product open every month — what it does, what it cost to build, what the pipeline behind it looks like, and what the numbers did. One email a month, nothing in between.

Double opt-in — we send one confirmation link and nothing else until you click it.

RuleStack

Built by

Kynth Studios

the studio behind ToolDrift, StillShipping and BlockDex

part of Toolproof, the measurement layer for AI agent tooling

Directory

Configs
Stacks
Compare formats
AGENTS.md vs CLAUDE.md
Cursor rules alternatives
Diff two configs
Best AGENTS.md examples
Best Cursor rules examples
What goes in a CLAUDE.md

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

© 2026 RuleStack. A Kynth Studios product. Changelog

RuleStack