Skip to content

Commit c7264ee

Browse files
authored
Merge pull request #4 from inmve/move-memory-files-to-top
Move memory files technique to top priority
2 parents 8496dac + 8d9cc79 commit c7264ee

File tree

1 file changed

+57
-22
lines changed

1 file changed

+57
-22
lines changed

README.md

Lines changed: 57 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -44,38 +44,45 @@ This curated collection fills in those gaps. It's a living document, and you're
4444

4545
## Requirements & Planning
4646

47-
### Read, Plan, Code, Commit
48-
49-
Make it explore the code, then make a plan, implement it, and commit.
50-
51-
> "There's a process that I call 'priming' the agent, where instead of having the agent jump straight to performing a task, I have it read additional context upfront to increase the chances that it will produce good outputs."
52-
> [Indragie Karunaratne](https://www.indragie.com/blog/i-shipped-a-macos-app-built-entirely-by-claude-code#:~:text=There's%20a%20process%20that%20I%20call)
53-
5447
### Set Up Memory Files
5548

5649
Create context files that persistently guide tools about your project's structure, standards, and preferences.
5750

5851
> "`CLAUDE.md` is a special file that Claude automatically pulls into context when starting a conversation. This makes it an ideal place for documenting: common bash commands, core files and utility functions, code style guidelines, testing instructions."
5952
> [Anthropic](https://www.anthropic.com/engineering/claude-code-best-practices#:~:text=CLAUDE.md%20is%20a%20special%20file)
6053
54+
**Tool Implementations:**
55+
6156
<details>
62-
<summary><strong>🛠️ Tool Implementations</strong></summary>
57+
<summary><strong>Claude Code</strong></summary>
6358

64-
**Claude Code**: Run `/init` to auto-generate smart context files that make Claude understand your codebase instantly. Claude analyzes dependencies, scripts, and architecture automatically. Use `/memory` to edit and add project-specific gotchas.
59+
Run `/init` to auto-generate smart context files that make Claude understand your codebase instantly. Claude analyzes dependencies, scripts, and architecture automatically. Use `/memory` to edit and add project-specific gotchas.
6560

6661
- For new projects: Run `/init` in your project root to create a starter `CLAUDE.md`
6762
- For existing codebases: Run `/init` and Claude will analyze your project structure, dependencies, and configuration files to automatically generate essential information
6863
- Use `/memory` for full editor interface or `#` as quick shortcut to add notes
6964
- Memory file hierarchy: `~/.claude/CLAUDE.md` (global) and `./CLAUDE.md` (project-specific)
7065

71-
**Cursor**: Create `AGENTS.md` for project rules, then use @codebase and @docs for dynamic context. Cursor's superpower is real-time understanding of your entire codebase through @-mentions.
66+
</details>
67+
68+
<details>
69+
<summary><strong>Cursor</strong></summary>
70+
71+
Create `AGENTS.md` for project rules, then use @codebase and @docs for dynamic context. Cursor's superpower is real-time understanding of your entire codebase through @-mentions.
7272

7373
- Create `AGENTS.md` at project root (also supports legacy `.cursorrules`)
7474
- Real-time context: Use `@codebase` to pull in relevant files automatically, `@docs` to reference documentation, `@git` to understand recent changes
7575
- Combine static rules (AGENTS.md) with dynamic context (@-mentions) for best results
7676

7777
</details>
7878

79+
### Read, Plan, Code, Commit
80+
81+
Make it explore the code, then make a plan, implement it, and commit.
82+
83+
> "There's a process that I call 'priming' the agent, where instead of having the agent jump straight to performing a task, I have it read additional context upfront to increase the chances that it will produce good outputs."
84+
> [Indragie Karunaratne](https://www.indragie.com/blog/i-shipped-a-macos-app-built-entirely-by-claude-code#:~:text=There's%20a%20process%20that%20I%20call)
85+
7986
### Write Detailed Specs
8087

8188
Give comprehensive specs - even a conversational spec beats vague instructions.
@@ -276,18 +283,25 @@ Stop waiting for one AI agent to finish before starting another - run multiple a
276283
> "I disable all permission checks. Which basically means I run claude --dangerously-skip-permissions. More specifically I have an alias called claude-yolo set up."
277284
> [Armin Ronacher](https://lucumr.pocoo.org/2025/6/12/agentic-coding/#:~:text=I%20disable%20all%20permission%20checks)
278285
286+
**Tool Implementations:**
287+
279288
<details>
280-
<summary><strong>🛠️ Tool Implementations</strong></summary>
289+
<summary><strong>Claude Code</strong></summary>
281290

282-
**Claude Code**: Use `--dangerously-skip-permissions` on launch or `/permissions` to change permission strategy during coding session.
291+
Use `--dangerously-skip-permissions` on launch or `/permissions` to change permission strategy during coding session.
283292

284293
- Run `claude --dangerously-skip-permissions` to enable autonomous mode where Claude runs uninterrupted without permission prompts
285294
- Switch during session: Use `/permissions` to manage tool permissions mid-session without restarting
286295
- When to use: Fixing lint errors across multiple files, simple refactoring and variable renames, routine code updates and migrations
287296
- Safety: Best used in containers or VMs for isolation, avoid on critical production systems
288297
- Setup alias: Many users create `alias cc='claude --dangerously-skip-permissions'` for quick access
289298

290-
**Codex CLI**: Use `--full-auto` on launch or `/mode` to change permission strategy during coding session.
299+
</details>
300+
301+
<details>
302+
<summary><strong>Codex CLI</strong></summary>
303+
304+
Use `--full-auto` on launch or `/mode` to change permission strategy during coding session.
291305

292306
- Enable full autonomous mode with `codex --full-auto` or use in-session `/mode` command
293307
- Switch during session: Use `/mode` to hot-swap between permission levels without losing session context
@@ -310,16 +324,23 @@ Begin with faster/cheaper models for routine tasks, then escalate to more powerf
310324
> "Sonnet 4 handles 90% of tasks effectively. Switch to Opus when Sonnet gets stuck. Recommend starting with Sonnet and providing comprehensive context."
311325
> [Sankalp](https://sankalp.bearblog.dev/my-claude-code-experience-after-2-weeks-of-usage/#:~:text=Sonnet%204%20handles%2090%25)
312326
327+
**Tool Implementations:**
328+
313329
<details>
314-
<summary><strong>🛠️ Tool Implementations</strong></summary>
330+
<summary><strong>Claude Code</strong></summary>
315331

316-
**Claude Code**: Use `/model` to switch between models based on task complexity. Start with cheaper Sonnet 4 for routine work, escalate to fast Opus 4.1 when stuck.
332+
Use `/model` to switch between models based on task complexity. Start with cheaper Sonnet 4 for routine work, escalate to fast Opus 4.1 when stuck.
317333

318334
- Use `/model` to switch models during your session
319335
- Cheaper, faster option: `Claude Sonnet 4`
320336
- Top-graded option: `Claude Opus 4.1`
321337

322-
**Codex CLI**: Use `/model` to escalate when needed. Start with `gpt-5-medium` for most tasks, switch to `gpt-5-high` when you hit complex problems.
338+
</details>
339+
340+
<details>
341+
<summary><strong>Codex CLI</strong></summary>
342+
343+
Use `/model` to escalate when needed. Start with `gpt-5-medium` for most tasks, switch to `gpt-5-high` when you hit complex problems.
323344

324345
- Use `/model` to switch models during your session
325346
- Cheaper, faster option: `gpt-5-medium`
@@ -341,16 +362,23 @@ Reset the AI's context window between unrelated tasks to prevent confusion and i
341362
> "During long sessions, Claude's context window can fill with irrelevant conversation, file contents, and commands. This can reduce performance and sometimes distract Claude. Use the `/clear` command frequently between tasks to reset the context window."
342363
> [Anthropic](https://www.anthropic.com/engineering/claude-code-best-practices#:~:text=During%20long%20sessions%2C%20Claude's%20context)
343364
365+
**Tool Implementations:**
366+
344367
<details>
345-
<summary><strong>🛠️ Tool Implementations</strong></summary>
368+
<summary><strong>Claude Code</strong></summary>
346369

347-
**Claude Code**: Use `/clear` command to reset the context window and start fresh.
370+
Use `/clear` command to reset the context window and start fresh.
348371

349372
- Run `/clear` between unrelated tasks to prevent context pollution
350373
- Preserves your memory files (CLAUDE.md) while clearing conversation history
351374
- Essential for long coding sessions to maintain performance
352375

353-
**Cursor**: Start new chat sessions or use conversation management features.
376+
</details>
377+
378+
<details>
379+
<summary><strong>Cursor</strong></summary>
380+
381+
Start new chat sessions or use conversation management features.
354382

355383
- Use Cmd/Ctrl+Shift+L to start a new chat for unrelated tasks
356384
- Chat history is automatically managed to prevent context overload
@@ -372,17 +400,24 @@ Don't let AI go too far down the wrong path - interrupt, provide feedback, and r
372400
> "Press Escape to interrupt Claude during any phase (thinking, tool calls, file edits), preserving context so you can redirect or expand instructions. Double-tap Escape to jump back in history, edit a previous prompt, and explore a different direction. You can edit the prompt and repeat until you get the result you're looking for."
373401
> [Anthropic](https://www.anthropic.com/engineering/claude-code-best-practices#:~:text=Press%20Escape%20to%20interrupt%20Claude)
374402
403+
**Tool Implementations:**
404+
375405
<details>
376-
<summary><strong>🛠️ Tool Implementations</strong></summary>
406+
<summary><strong>Claude Code</strong></summary>
377407

378-
**Claude Code**: Use Escape key to interrupt and redirect Claude at any time.
408+
Use Escape key to interrupt and redirect Claude at any time.
379409

380410
- Press `Escape` to interrupt Claude during any phase (thinking, tool calls, file edits)
381411
- Double-tap `Escape` to jump back in history and edit a previous prompt
382412
- Context is preserved so you can redirect or expand instructions
383413
- Edit the prompt and retry until you get the desired result
384414

385-
**Cursor**: Use Cmd/Ctrl+K to stop generation and provide new instructions.
415+
</details>
416+
417+
<details>
418+
<summary><strong>Cursor</strong></summary>
419+
420+
Use Cmd/Ctrl+K to stop generation and provide new instructions.
386421

387422
- Stop generation with `Cmd/Ctrl+K` when you see it going off track
388423
- Provide corrective feedback immediately rather than waiting

0 commit comments

Comments
 (0)