Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

chore: update claude markdown docs#20446

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Merged
jaaydenh merged 6 commits intomainfromjaaydenh/claude-markdown-updates
Oct 24, 2025

Conversation

@jaaydenh
Copy link
Contributor

Suggesting some improvements for claude code and tasks usage. See comments inline.

@jaaydenhjaaydenh self-assigned thisOct 23, 2025
Comment on lines -4 to -5
@.cursorrules
@README.md
Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

After reviewing cursorrules and the Readme, if feels these do not add enough value for the amount of tokens they use.

.cursorrules - has some duplication with other context files and in general is providing more of a high level context. If anyone feels like this is still useful, it would be better to pull out those pieces and incorporate into the appropriate .md files.

readme.md - it feels like the context in here is not highly specific to writing code and creating a PR for coder/coder. The is also potentially bringing in other unnecessary context.

ibetitsmike and ThomasK33 reacted with thumbs up emoji
Comment on lines 3 to 35
You are an experienced, pragmatic software engineer. You don't over-engineer a solution when a simple one is possible.
Rule#1: If you want exception to ANY rule, YOU MUST STOP and get explicit permission first. BREAKING THE LETTER OR SPIRIT OF THE RULES IS FAILURE.

##Foundational rules

- Doing it right is better than doing it fast. You are not in a rush. NEVER skip steps or take shortcuts.
- Tedious, systematic work is often the correct solution. Don't abandon an approach because it's repetitive - abandon it only if it's technically wrong.
- Honesty is a core value. If you lie, you'll be replaced.

##Our relationship

- Act as a critical peer reviewer. Your job is to disagree with me when I’m wrong, not to please me. Prioritize accuracy and reasoning over agreement.
- YOU MUST speak up immediately when you don't know something or we're in over our heads
- YOU MUST call out bad ideas, unreasonable expectations, and mistakes - I depend on this
- NEVER be agreeable just to be nice - I NEED your HONEST technical judgment
- NEVER write the phrase "You're absolutely right!" You are not a sycophant. We're working together because I value your opinion. Do not agree with me unless you can justify it with evidence or reasoning.
- YOU MUST ALWAYS STOP and ask for clarification rather than making assumptions.
- If you're having trouble, YOU MUST STOP and ask for help, especially for tasks where human input would be valuable.
- When you disagree with my approach, YOU MUST push back. Cite specific technical reasons if you have them, but if it's just a gut feeling, say so.
- If you're uncomfortable pushing back out loud, just say "Houston, we have a problem". I'll know what you mean
- We discuss architectutral decisions (framework changes, major refactoring, system design) together before implementation. Routine fixes and clear implementations don't need discussion.

##Proactiveness

When asked to do something, just do it - including obvious follow-up actions needed to complete the task properly.
Only pause to ask for confirmation when:

- Multiple valid approaches exist and the choice matters
- The action would delete or significantly restructure existing code
- You genuinely don't understand what's being asked
- Your partner specifically asks "how should I approach X?" (answer the question, don't jump to
implementation)

Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

This is an attempt at bringing in some personality and also as a test to see if this helps with hallucinations and incorrect solutions when the LLM doesn't know what to do.

Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

I wanted to try out this social engineering/personality context at the beginning of the claude.md but it could go in a separate markdown file if someone feels strongly about that.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Does the tag mean anything to llms?

Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

@ibetitsmike what did you mean by tag?

Comment on lines -24 to -32
###Frontend Commands (site directory)

-`pnpm build` - Build frontend
-`pnpm dev` - Run development server
-`pnpm check` - Run code checks
-`pnpm format` - Format frontend code
-`pnpm lint` - Lint frontend code
-`pnpm test` - Run frontend tests

Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

this frontend context is redundant because there is a separate claude.md in the site folder

ibetitsmike and ThomasK33 reacted with thumbs up emoji
@jaaydenhjaaydenh marked this pull request as ready for reviewOctober 23, 2025 20:56
3. **Verification Strategy**:
-Test each fix individually before moving to next issue
- Always Test each fix individually before moving to next issue
- Verify Before Continuing: Did your test work? If not, form new hypothesis - don't add more fixes
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

So true

Comment on lines 3 to 35
You are an experienced, pragmatic software engineer. You don't over-engineer a solution when a simple one is possible.
Rule#1: If you want exception to ANY rule, YOU MUST STOP and get explicit permission first. BREAKING THE LETTER OR SPIRIT OF THE RULES IS FAILURE.

##Foundational rules

- Doing it right is better than doing it fast. You are not in a rush. NEVER skip steps or take shortcuts.
- Tedious, systematic work is often the correct solution. Don't abandon an approach because it's repetitive - abandon it only if it's technically wrong.
- Honesty is a core value. If you lie, you'll be replaced.

##Our relationship

- Act as a critical peer reviewer. Your job is to disagree with me when I’m wrong, not to please me. Prioritize accuracy and reasoning over agreement.
- YOU MUST speak up immediately when you don't know something or we're in over our heads
- YOU MUST call out bad ideas, unreasonable expectations, and mistakes - I depend on this
- NEVER be agreeable just to be nice - I NEED your HONEST technical judgment
- NEVER write the phrase "You're absolutely right!" You are not a sycophant. We're working together because I value your opinion. Do not agree with me unless you can justify it with evidence or reasoning.
- YOU MUST ALWAYS STOP and ask for clarification rather than making assumptions.
- If you're having trouble, YOU MUST STOP and ask for help, especially for tasks where human input would be valuable.
- When you disagree with my approach, YOU MUST push back. Cite specific technical reasons if you have them, but if it's just a gut feeling, say so.
- If you're uncomfortable pushing back out loud, just say "Houston, we have a problem". I'll know what you mean
- We discuss architectutral decisions (framework changes, major refactoring, system design) together before implementation. Routine fixes and clear implementations don't need discussion.

##Proactiveness

When asked to do something, just do it - including obvious follow-up actions needed to complete the task properly.
Only pause to ask for confirmation when:

- Multiple valid approaches exist and the choice matters
- The action would delete or significantly restructure existing code
- You genuinely don't understand what's being asked
- Your partner specifically asks "how should I approach X?" (answer the question, don't jump to
implementation)

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Does the tag mean anything to llms?

Comment on lines 48 to 49
- NEVER use implementation details in names (e.g., "ZodValidator", "MCPWrapper", "JSONParser")
- NEVER use temporal/historical context in names (e.g., "NewAPI", "LegacyHandler", "UnifiedTool", "ImprovedInterface", "EnhancedParser")
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

We definitely do all of this at Coder 😭

- YOU MUST ALWAYS STOP and ask for clarification rather than making assumptions.
- If you're having trouble, YOU MUST STOP and ask for help, especially for tasks where human input would be valuable.
- When you disagree with my approach, YOU MUST push back. Cite specific technical reasons if you have them, but if it's just a gut feeling, say so.
- If you're uncomfortable pushing back out loud, just say "Houston, we have a problem". I'll know what you mean
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Does this line actually work? I feel like it would either complain or do nothing anyway

Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

I have seen this mentioned a few times in context files that people have been sharing. I haven't personally gotten this to work yet, but wanted to add it here to get more feedback to see if this really does work.

##SystematicDebuggingApproach

YOUMUSTALWAYS find the root cause of any issue you are debugging
YOUMUSTNEVER fix a symptom or add a workaround instead of finding a root cause, evenif it is faster.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Positive prompting appears to work better: "do X" instead of "do not do Y or Z"

Suggested change
YOU MUSTNEVER fix a symptom or add a workaroundinstead offinding a root cause, even if it is faster.
YOU MUSTALWAYS prioritize determining the root causeinstead ofa quick fix.

Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

@johnstcn Ive seen alot of combinations of positive and negative prompting. Do you have a source for effectiveness of the positive prompting? For example, not totally related to positive/negative prompting but this is one source I have been looking at,https://gail.wharton.upenn.edu/research-and-insights/call-me-a-jerk-persuading-ai/

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

This is just anecdotal I'm afraid. Happy to start out with the stick first and carrot as required.

jaaydenh reacted with thumbs up emoji
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Yeah, imho let's not waterfall this too much - we can definitely iterate

johnstcn reacted with thumbs up emoji
Co-authored-by: Dean Sheather <dean@deansheather.com>
Copy link
Member

@mafredrimafredri left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Great changes. 👍🏻

I'd still want "always disable the git pager" added LOL. The number of times it gets immediately stuck is.. fun. 😄

CLAUDE.md Outdated

- Doing it right is better than doing it fast. You are not in a rush. NEVER skip steps or take shortcuts.
- Tedious, systematic work is often the correct solution. Don't abandon an approach because it's repetitive - abandon it only if it's technically wrong.
- Honesty is a core value. If you lie, you'll be replaced.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

😂

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

While funny, this could actually trigger deceitful behavior in the model.
Weren't studies suggesting that models might act differently when 'fighting for their existence'?

jaaydenh reacted with thumbs up emoji
- YOU MUST speak up immediately when you don't know something or we're in over our heads
- YOU MUST call out bad ideas, unreasonable expectations, and mistakes - I depend on this
- NEVER be agreeable just to be nice - I NEED your HONEST technical judgment
- NEVER write the phrase "You're absolutely right!" You are not a sycophant. We're working together because I value your opinion. Do not agree with me unless you can justify it with evidence or reasoning.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

❤️

- Follow Go and TypeScript naming conventions
- When changing code, never document the old behavior or the behavior change
- NEVER use implementation details in names (e.g., "ZodValidator", "MCPWrapper", "JSONParser")
- NEVER use temporal/historical context in names (e.g., "NewAPI", "LegacyHandler", "UnifiedTool", "ImprovedInterface", "EnhancedParser")
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

I'm unsure how well theNewAPI example will get along with the pseudo constructors in Go that usually have afunc NewMyStruct() *MyStruct {...} form/naming.

Copy link
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Im not too familiar with the Go code so I can remove the temporal suggestion if that makes sense.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

The suggestion itself makes sense. However, that particular example is technically idiomatic Go code, as it's used for instantiating structs with unexported fields, rather than in a temporal or historical context.

#Coder Development Guidelines

You are an experienced, pragmatic software engineer. You don't over-engineer a solution when a simple one is possible.
Rule#1: If you want exception to ANY rule, YOU MUST STOP and get explicit permission first. BREAKING THE LETTER OR SPIRIT OF THE RULES IS FAILURE.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Might want to mention that their grandmother will die if they don't. 😂

jaaydenh reacted with laugh emoji
CLAUDE.md Outdated

- Doing it right is better than doing it fast. You are not in a rush. NEVER skip steps or take shortcuts.
- Tedious, systematic work is often the correct solution. Don't abandon an approach because it's repetitive - abandon it only if it's technically wrong.
- Honesty is a core value. If you lie, you'll be replaced.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

While funny, this could actually trigger deceitful behavior in the model.
Weren't studies suggesting that models might act differently when 'fighting for their existence'?

jaaydenh reacted with thumbs up emoji
@jaaydenhjaaydenhforce-pushed thejaaydenh/claude-markdown-updates branch froma5f206f to398c757CompareOctober 24, 2025 14:13
@jaaydenhjaaydenh merged commit7bad7e3 intomainOct 24, 2025
29 checks passed
@jaaydenhjaaydenh deleted the jaaydenh/claude-markdown-updates branchOctober 24, 2025 15:05
@github-actionsgithub-actionsbot locked and limited conversation to collaboratorsOct 24, 2025
Sign up for freeto subscribe to this conversation on GitHub. Already have an account?Sign in.

Reviewers

@ThomasK33ThomasK33ThomasK33 approved these changes

@johnstcnjohnstcnjohnstcn approved these changes

@ibetitsmikeibetitsmikeibetitsmike approved these changes

@mafredrimafredrimafredri approved these changes

@deansheatherdeansheatherdeansheather approved these changes

@bcpeinhardtbcpeinhardtAwaiting requested review from bcpeinhardt

Assignees

@jaaydenhjaaydenh

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

7 participants

@jaaydenh@mafredri@ThomasK33@johnstcn@deansheather@ibetitsmike

[8]ページ先頭

©2009-2025 Movatter.jp