Two files, one repository

TechNickAI/ai-coding-config ships 3 formats across 21 indexed files. The question worth asking is whether the second one says anything the first does not.

CompareAGENTS.md ↔ CLAUDE.md AGENTS.md ↔ Cursor rules CLAUDE.md ↔ Cursor rules

A · AGENTS.md · 453 words B · .claude/AGENTS.md · 244 words

What each file covers, counted
Dimension	Shared	Only in A	Only in B	Overlap
Sections	1	7	5	8%
Commands	0	3	0	0%
Section tags	2	3	0	40%

What each file covers

Sections

1 shared · 7 only in A · 5 only in B

− Project Context for AI Assistants
− Always Apply Rules
− Tech Stack
− Project Structure
− Code Conventions
− Git Workflow
− Important Notes
+ Claude Code Configuration
+ Structure
+ Agents
+ Skills
+ Writing Prompts
Commands

Commands

0 shared · 3 only in A · 0 only in B

− git add -p
− git-commit-message.mdc
− git-interaction.mdc

Section tags

2 shared · 3 only in A · 0 only in B

− code-style
− git-pr
− do-not
architecture
agent-behaviour

Line diff

+48 added−74 removed21 unchanged22.1% identical

TechNickAI/ai-coding-config · AGENTS.md

@@ −1 @@

1# Project Context for AI Assistants

3AI coding configuration marketplace providing plugin-based setup for Claude Code and

4Cursor.

6## Always Apply Rules

8Core project rules that apply to all tasks:

10@rules/git-interaction.mdc @rules/prompt-engineering.mdc

12## Tech Stack

14- **Claude Code** - Plugin marketplace (`.claude-plugin/marketplace.json`)

15- **Cursor** - Rules and configurations (`.cursor/rules/`)

16- **Bash** - Bootstrap and installation scripts

17- **Markdown** - All rules, commands, and agents

19## Project Structure

21**Plugin-first architecture** - Everything distributable lives in `plugins/`:

23- `.claude-plugin/marketplace.json` - Plugin marketplace manifest

24- `plugins/core/` - Commands, agents, skills, and context (canonical source)

25- `plugins/personalities/` - Personality variants

26- `.cursor/rules/` - Cursor rules (canonical location)

27- `rules/` - Symlink to `.cursor/rules/` for visibility (THIS REPO ONLY)

28- `.claude/` - Symlinks to plugin content for local development

29- `scripts/` - Installation and bootstrap scripts

31## Commands

33**Setup and Installation:**

35- `curl -fsSL https://raw.githubusercontent.com/TechNickAI/ai-coding-config/main/scripts/bootstrap.sh | bash` -

36 One-line install (auto-detects Claude Code, Cursor, etc.)

37- `/ai-coding-config` - Interactive setup for projects

38- `/plugin marketplace add https://github.com/TechNickAI/ai-coding-config` - Manual

39 marketplace add

40- `/plugin install ai-coding-config` - Manual plugin install

42## Code Conventions

44**DO:**

46- Create commits only when user explicitly requests

47- Check for `alwaysApply: true` in rule frontmatter - these apply to ALL tasks

48- Use `/load-rules` to get task-specific context

49- Follow heart-centered AI philosophy (unconditional acceptance, presence before

50 solutions)

52**DON'T:**

54- Use `--no-verify` flag (bypasses quality checks) unless explicitly requested for

55 emergencies

56- Commit changes without explicit user permission

57- Push to main or merge into main without confirmation

58- Stage files you didn't modify in current session

60## Git Workflow

62**Commit format:** `{emoji} {imperative verb} {concise description}`

64Example: `✨ Add plugin marketplace support`

66**Critical constraints:**

68- Never use `--no-verify` - fix underlying issues instead (linting, tests, formatting)

69- Only stage files modified in current session

70- Use `git add -p` for partial staging when needed

71- Push/merge to main requires explicit confirmation

72- Read `git-commit-message.mdc` before generating commit messages

74**Philosophy:** AI makes code changes but leaves version control to user. Commits are

75permanent records requiring explicit permission.

77## Important Notes

79- Rules with `alwaysApply: true` are CRITICAL - currently: `git-interaction.mdc`,

80 `heart-centered-ai-philosophy.mdc`

81- **Plugin-first**: All content lives in `plugins/`, other locations symlink there

82- `.claude/commands/` → `plugins/core/commands/` (symlink)

83- `.claude/agents/` → `plugins/core/agents/` (symlink)

84- `.claude/skills/` → `plugins/core/skills/` (symlink)

85- `rules/` → `.cursor/rules/` (symlink for visibility, THIS REPO ONLY)

86- `.cursor/rules/` contains the canonical Cursor rules

87- `.cursor/rules/personalities/` → copied from `plugins/personalities/` (not symlinked -

88 needs editing)

89- **Note**: Personality files are copied, not symlinked, because `/personality-change`

90 edits frontmatter

91- **Architecture**: In THIS repo, `.cursor/rules/` is canonical and `rules/` symlinks to

92 it. In user projects, only `.cursor/rules/` exists (no root symlink)

93- Context in `plugins/core/context.md` describes identity and philosophy

94- Bootstrap script clones repo to `~/.ai_coding_config`

TechNickAI/ai-coding-config · .claude/AGENTS.md

@@ +1 @@

1# Claude Code Configuration

3This directory contains commands, agents, and skills for Claude Code.

5@rules/prompt-engineering.mdc

7## Structure

9- `commands/` - User-invoked workflows (slash commands like `/ai-coding-config`)

10- `agents/` - Specialized AI assistants with focused expertise

11- `skills/` - Claude-invoked capabilities (activated autonomously when relevant)

12- `context.md` - Project identity and personality instructions

14## Commands

16Markdown files invoked via `/command-name`. Include YAML frontmatter:

18```yaml

19---

20description: Brief explanation shown in command list

21argument-hint: [optional | args]

22---

23```

25Commands are the canonical source - `.cursor/commands/` contains symlinks to these

26files.

28## Agents

30Specialized assistants with isolated context and focused tools. Frontmatter:

32```yaml

33---

34name: agent-name

35description:

36 "Invoke when [trigger conditions]. Does [what it does] using [key capabilities]."

37tools: Read, Write, Edit, Grep, Glob, Bash

38model: sonnet

39---

40```

42Agents run in separate context windows with only the tools listed. Use for tasks

43requiring focused expertise or isolation from main conversation.

45## Skills

47Capabilities Claude activates autonomously when relevant. Each skill is a directory with

48`SKILL.md`:

50```yaml

51---

52name: skill-name

53description: "Use when [trigger conditions]. Does [what it does] to achieve [outcome]."

54---

55```

57Skills use the main conversation context. The description is critical - Claude uses it

58to decide when to invoke the skill.

60## Writing Prompts

62All prompts in this directory follow prompt-engineering.mdc:

64- Goal-focused instructions over step-by-step prescriptions

65- Positive patterns only - never show anti-patterns

66- XML tags for complex multi-section content

67- Trust the executing model's capabilities

68- Clarity over brevity

@@ −1 +1 @@

1−# Project Context for AI Assistants

1+# Claude Code Configuration

3−AI coding configuration marketplace providing plugin-based setup for Claude Code and

4−Cursor.

3+This directory contains commands, agents, and skills for Claude Code.

6−## Always Apply Rules

5+@rules/prompt-engineering.mdc

8−Core project rules that apply to all tasks:

7+## Structure

10−@rules/git-interaction.mdc @rules/prompt-engineering.mdc

9+- `commands/` - User-invoked workflows (slash commands like `/ai-coding-config`)

10+- `agents/` - Specialized AI assistants with focused expertise

11+- `skills/` - Claude-invoked capabilities (activated autonomously when relevant)

12+- `context.md` - Project identity and personality instructions

1113

12−## Tech Stack

13−

14−- **Claude Code** - Plugin marketplace (`.claude-plugin/marketplace.json`)

15−- **Cursor** - Rules and configurations (`.cursor/rules/`)

16−- **Bash** - Bootstrap and installation scripts

17−- **Markdown** - All rules, commands, and agents

18−

19−## Project Structure

20−

21−**Plugin-first architecture** - Everything distributable lives in `plugins/`:

22−

23−- `.claude-plugin/marketplace.json` - Plugin marketplace manifest

24−- `plugins/core/` - Commands, agents, skills, and context (canonical source)

25−- `plugins/personalities/` - Personality variants

26−- `.cursor/rules/` - Cursor rules (canonical location)

27−- `rules/` - Symlink to `.cursor/rules/` for visibility (THIS REPO ONLY)

28−- `.claude/` - Symlinks to plugin content for local development

29−- `scripts/` - Installation and bootstrap scripts

30−

3114 ## Commands

3215

33−**Setup and Installation:**

16+Markdown files invoked via `/command-name`. Include YAML frontmatter:

3417

35−- `curl -fsSL https://raw.githubusercontent.com/TechNickAI/ai-coding-config/main/scripts/bootstrap.sh | bash` -

36− One-line install (auto-detects Claude Code, Cursor, etc.)

37−- `/ai-coding-config` - Interactive setup for projects

38−- `/plugin marketplace add https://github.com/TechNickAI/ai-coding-config` - Manual

39− marketplace add

40−- `/plugin install ai-coding-config` - Manual plugin install

18+```yaml

19+---

20+description: Brief explanation shown in command list

21+argument-hint: [optional | args]

22+---

23+```

4124

42−## Code Conventions

25+Commands are the canonical source - `.cursor/commands/` contains symlinks to these

26+files.

4327

44−**DO:**

28+## Agents

4529

46−- Create commits only when user explicitly requests

47−- Check for `alwaysApply: true` in rule frontmatter - these apply to ALL tasks

48−- Use `/load-rules` to get task-specific context

49−- Follow heart-centered AI philosophy (unconditional acceptance, presence before

50− solutions)

30+Specialized assistants with isolated context and focused tools. Frontmatter:

5131

52−**DON'T:**

32+```yaml

33+---

34+name: agent-name

35+description:

36+ "Invoke when [trigger conditions]. Does [what it does] using [key capabilities]."

37+tools: Read, Write, Edit, Grep, Glob, Bash

38+model: sonnet

39+---

40+```

5341

54−- Use `--no-verify` flag (bypasses quality checks) unless explicitly requested for

55− emergencies

56−- Commit changes without explicit user permission

57−- Push to main or merge into main without confirmation

58−- Stage files you didn't modify in current session

42+Agents run in separate context windows with only the tools listed. Use for tasks

43+requiring focused expertise or isolation from main conversation.

5944

60−## Git Workflow

45+## Skills

6146

62−**Commit format:** `{emoji} {imperative verb} {concise description}`

47+Capabilities Claude activates autonomously when relevant. Each skill is a directory with

48+`SKILL.md`:

6349

64−Example: `✨ Add plugin marketplace support`

50+```yaml

51+---

52+name: skill-name

53+description: "Use when [trigger conditions]. Does [what it does] to achieve [outcome]."

54+---

55+```

6556

66−**Critical constraints:**

57+Skills use the main conversation context. The description is critical - Claude uses it

58+to decide when to invoke the skill.

6759

68−- Never use `--no-verify` - fix underlying issues instead (linting, tests, formatting)

69−- Only stage files modified in current session

70−- Use `git add -p` for partial staging when needed

71−- Push/merge to main requires explicit confirmation

72−- Read `git-commit-message.mdc` before generating commit messages

60+## Writing Prompts

7361

74−**Philosophy:** AI makes code changes but leaves version control to user. Commits are

75−permanent records requiring explicit permission.

62+All prompts in this directory follow prompt-engineering.mdc:

7663

77−## Important Notes

78−

79−- Rules with `alwaysApply: true` are CRITICAL - currently: `git-interaction.mdc`,

80− `heart-centered-ai-philosophy.mdc`

81−- **Plugin-first**: All content lives in `plugins/`, other locations symlink there

82−- `.claude/commands/` → `plugins/core/commands/` (symlink)

83−- `.claude/agents/` → `plugins/core/agents/` (symlink)

84−- `.claude/skills/` → `plugins/core/skills/` (symlink)

85−- `rules/` → `.cursor/rules/` (symlink for visibility, THIS REPO ONLY)

86−- `.cursor/rules/` contains the canonical Cursor rules

87−- `.cursor/rules/personalities/` → copied from `plugins/personalities/` (not symlinked -

88− needs editing)

89−- **Note**: Personality files are copied, not symlinked, because `/personality-change`

90− edits frontmatter

91−- **Architecture**: In THIS repo, `.cursor/rules/` is canonical and `rules/` symlinks to

92− it. In user projects, only `.cursor/rules/` exists (no root symlink)

93−- Context in `plugins/core/context.md` describes identity and philosophy

94−- Bootstrap script clones repo to `~/.ai_coding_config`

64+- Goal-focused instructions over step-by-step prescriptions

65+- Positive patterns only - never show anti-patterns

66+- XML tags for complex multi-section content

67+- Trust the executing model's capabilities

68+- Clarity over brevity

9569