RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Diff/harritaito-harritaito-github-io-claude ↔ harritaito-harritaito-github-io-codex-agents

Comparison

A · CLAUDE.md · harritaito/harritaito.github.ioB · AGENTS.md · harritaito/harritaito.github.io
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections0520%
Commands0020%
Section tags10420%

What each file covers

Sections

0 shared · 5 only in A · 2 only in B
  • − CLAUDE.md
  • − 1. Think Before Coding
  • − 2. Simplicity First
  • − 3. Surgical Changes
  • − 4. Goal-Driven Execution
  • + ~/.codex/AGENTS.md (project-local profile)
  • + Working agreements

Commands

0 shared · 0 only in A · 2 only in B
  • + npm test
  • + npm run build

Section tags

1 shared · 0 only in A · 4 only in B
  • + build
  • + test
  • + code-style
  • + git-pr
  •   agent-behaviour

Line diff

+7 added−63 removed3 unchanged4.5% identical
harritaito/harritaito.github.io · CLAUDE.md
@@ −1 @@
1# CLAUDE.md
2 
3Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
4 
5**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
6 
7## 1. Think Before Coding
8 
9**Don't assume. Don't hide confusion. Surface tradeoffs.**
10 
11Before implementing:
12- State your assumptions explicitly. If uncertain, ask.
13- If multiple interpretations exist, present them - don't pick silently.
14- If a simpler approach exists, say so. Push back when warranted.
15- If something is unclear, stop. Name what's confusing. Ask.
16 
17## 2. Simplicity First
18 
19**Minimum code that solves the problem. Nothing speculative.**
20 
21- No features beyond what was asked.
22- No abstractions for single-use code.
23- No "flexibility" or "configurability" that wasn't requested.
24- No error handling for impossible scenarios.
25- If you write 200 lines and it could be 50, rewrite it.
26 
27Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
28 
29## 3. Surgical Changes
30 
31**Touch only what you must. Clean up only your own mess.**
32 
33When editing existing code:
34- Don't "improve" adjacent code, comments, or formatting.
35- Don't refactor things that aren't broken.
36- Match existing style, even if you'd do it differently.
37- If you notice unrelated dead code, mention it - don't delete it.
38 
39When your changes create orphans:
40- Remove imports/variables/functions that YOUR changes made unused.
41- Don't remove pre-existing dead code unless asked.
42 
43The test: Every changed line should trace directly to the user's request.
44 
45## 4. Goal-Driven Execution
46 
47**Define success criteria. Loop until verified.**
48 
49Transform tasks into verifiable goals:
50- "Add validation" → "Write tests for invalid inputs, then make them pass"
51- "Fix the bug" → "Write a test that reproduces it, then make it pass"
52- "Refactor X" → "Ensure tests pass before and after"
53 
54For multi-step tasks, state a brief plan:
55```
561. [Step] → verify: [check]
572. [Step] → verify: [check]
583. [Step] → verify: [check]
59```
60 
61Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
62 
63---
64 
65**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.
66 
harritaito/harritaito.github.io · .codex/AGENTS.md
@@ +1 @@
1# ~/.codex/AGENTS.md (project-local profile)
2 
3## Working agreements
4 
5- Run `npm test` and `npm run build` after code or documentation changes.
6- Prefer small, reviewable commits that follow Conventional Commits.
7- Keep `package-lock.json` unchanged unless a task explicitly requires dependency updates.
8- For docs updates, keep ATX headings and wrap lines to 100 characters.
9- Summarize which instruction files were applied when a task starts.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10 
@@ −1 +1 @@
1−# CLAUDE.md
1+# ~/.codex/AGENTS.md (project-local profile)
22  
3−Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
3+## Working agreements
44  
5−**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
6− 
7−## 1. Think Before Coding
8− 
9−**Don't assume. Don't hide confusion. Surface tradeoffs.**
10− 
11−Before implementing:
12−- State your assumptions explicitly. If uncertain, ask.
13−- If multiple interpretations exist, present them - don't pick silently.
14−- If a simpler approach exists, say so. Push back when warranted.
15−- If something is unclear, stop. Name what's confusing. Ask.
16− 
17−## 2. Simplicity First
18− 
19−**Minimum code that solves the problem. Nothing speculative.**
20− 
21−- No features beyond what was asked.
22−- No abstractions for single-use code.
23−- No "flexibility" or "configurability" that wasn't requested.
24−- No error handling for impossible scenarios.
25−- If you write 200 lines and it could be 50, rewrite it.
26− 
27−Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
28− 
29−## 3. Surgical Changes
30− 
31−**Touch only what you must. Clean up only your own mess.**
32− 
33−When editing existing code:
34−- Don't "improve" adjacent code, comments, or formatting.
35−- Don't refactor things that aren't broken.
36−- Match existing style, even if you'd do it differently.
37−- If you notice unrelated dead code, mention it - don't delete it.
38− 
39−When your changes create orphans:
40−- Remove imports/variables/functions that YOUR changes made unused.
41−- Don't remove pre-existing dead code unless asked.
42− 
43−The test: Every changed line should trace directly to the user's request.
44− 
45−## 4. Goal-Driven Execution
46− 
47−**Define success criteria. Loop until verified.**
48− 
49−Transform tasks into verifiable goals:
50−- "Add validation" → "Write tests for invalid inputs, then make them pass"
51−- "Fix the bug" → "Write a test that reproduces it, then make it pass"
52−- "Refactor X" → "Ensure tests pass before and after"
53− 
54−For multi-step tasks, state a brief plan:
55−```
56−1. [Step] → verify: [check]
57−2. [Step] → verify: [check]
58−3. [Step] → verify: [check]
59−```
60− 
61−Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
62− 
63−---
64− 
65−**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.
5+- Run `npm test` and `npm run build` after code or documentation changes.
6+- Prefer small, reviewable commits that follow Conventional Commits.
7+- Keep `package-lock.json` unchanged unless a task explicitly requires dependency updates.
8+- For docs updates, keep ATX headings and wrap lines to 100 characters.
9+- Summarize which instruction files were applied when a task starts.
6610  
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack