added boris workflows with screenshots

This commit is contained in:
Shayan Rais
2026-03-13 13:27:58 +05:00
parent 5f16eb60b4
commit a06b8abfc5
25 changed files with 31 additions and 33 deletions
+2 -2
View File
@@ -1,7 +1,7 @@
# claude-code-best-practice # claude-code-best-practice
practice makes claude perfect practice makes claude perfect
![Last Updated](https://img.shields.io/badge/Last_Updated-Mar%2012%2C%202026%2006%3A29%20PM%20PKT-white?style=flat&labelColor=555) <a href="https://github.com/shanraisshan/claude-code-best-practice/stargazers"><img src="https://img.shields.io/github/stars/shanraisshan/claude-code-best-practice?style=flat&label=%E2%98%85&labelColor=555&color=white" alt="GitHub Stars"></a> ![Last Updated](https://img.shields.io/badge/Last_Updated-Mar%2013%2C%202026%2001%3A27%20PM%20PKT-white?style=flat&labelColor=555) <a href="https://github.com/shanraisshan/claude-code-best-practice/stargazers"><img src="https://img.shields.io/github/stars/shanraisshan/claude-code-best-practice?style=flat&label=%E2%98%85&labelColor=555&color=white" alt="GitHub Stars"></a>
[![Best Practice](!/tags/best-practice.svg)](best-practice/) *Click on this badge to show the latest best practice*<br> [![Best Practice](!/tags/best-practice.svg)](best-practice/) *Click on this badge to show the latest best practice*<br>
[![Implemented](!/tags/implemented.svg)](implementation/) *Click on this badge to show implementation in this repo*<br> [![Implemented](!/tags/implemented.svg)](implementation/) *Click on this badge to show implementation in this repo*<br>
@@ -138,7 +138,7 @@ claude
- use a [cross-model](development-workflows/cross-model-workflow/cross-model-workflow.md) for QA — e.g. [Codex](https://github.com/shanraisshan/codex-cli-best-practice) for plan and implementation review - use a [cross-model](development-workflows/cross-model-workflow/cross-model-workflow.md) for QA — e.g. [Codex](https://github.com/shanraisshan/codex-cli-best-practice) for plan and implementation review
**Utilities (5)** **Utilities (5)**
- [iTerm](https://iterm2.com/)/[Ghostty](https://ghostty.org/)/[tmux](https://github.com/tmux/tmux) terminals instead of IDE ([VS Code](https://code.visualstudio.com/)/[Cursor](https://www.cursor.com/)) - [iTerm](https://iterm2.com/)/[Ghostty](https://ghostty.org/) ([Boris tweet](https://x.com/bcherny/status/2017742753971769626))/[tmux](https://github.com/tmux/tmux) terminals instead of IDE ([VS Code](https://code.visualstudio.com/)/[Cursor](https://www.cursor.com/))
- [Wispr Flow](https://wisprflow.ai) for voice prompting (10x productivity) - [Wispr Flow](https://wisprflow.ai) for voice prompting (10x productivity)
- [claude-code-voice-hooks](https://github.com/shanraisshan/claude-code-voice-hooks) for claude feedback - [claude-code-voice-hooks](https://github.com/shanraisshan/claude-code-voice-hooks) for claude feedback
- [status line](https://github.com/shanraisshan/claude-code-status-line) for context awareness and fast compacting - [status line](https://github.com/shanraisshan/claude-code-status-line) for context awareness and fast compacting
+2 -4
View File
@@ -50,17 +50,15 @@ A comparison of the three extension mechanisms in Claude Code: subagents, comman
- You need a **user-initiated entry point** — a workflow the user explicitly triggers - You need a **user-initiated entry point** — a workflow the user explicitly triggers
- The workflow involves **orchestrating** other agents or skills - The workflow involves **orchestrating** other agents or skills
- You want **dynamic context injection** (`` !`git diff` ``, `` !`gh issue view $0` ``) to pull live data into the prompt - You want to **keep context lean** — command content is not injected into the session context until the user triggers it
- The task should run **inline** in the main conversation so the user sees everything
**Example**: `weather-orchestrator` — the user triggers it, it asks for C/F preference, invokes the agent, then invokes the SVG skill. **Example**: `weather-orchestrator` — the user triggers it, it asks for C/F preference, invokes the agent, then invokes the SVG skill.
### Use a Skill when: ### Use a Skill when:
- You want **Claude to auto-invoke** based on user intent (semantic matching via `description`) - You want **Claude to auto-invoke** based on user intent — skill descriptions are injected into the session context for semantic matching
- The task is a **reusable procedure** that can be invoked from multiple places (commands, agents, or Claude itself) - The task is a **reusable procedure** that can be invoked from multiple places (commands, agents, or Claude itself)
- You need **agent preloading** — baking domain knowledge into a specific agent at startup - You need **agent preloading** — baking domain knowledge into a specific agent at startup
- The task is **lightweight** and doesn't need a separate context window
**Example**: `weather-svg-creator` — Claude auto-invokes it when the user asks for a weather card; also callable from commands. **Example**: `weather-svg-creator` — Claude auto-invokes it when the user asks for a weather card; also callable from commands.

Before

Width:  |  Height:  |  Size: 74 KiB

After

Width:  |  Height:  |  Size: 74 KiB

Before

Width:  |  Height:  |  Size: 80 KiB

After

Width:  |  Height:  |  Size: 80 KiB

Before

Width:  |  Height:  |  Size: 49 KiB

After

Width:  |  Height:  |  Size: 49 KiB

Before

Width:  |  Height:  |  Size: 122 KiB

After

Width:  |  Height:  |  Size: 122 KiB

Before

Width:  |  Height:  |  Size: 78 KiB

After

Width:  |  Height:  |  Size: 78 KiB

Before

Width:  |  Height:  |  Size: 42 KiB

After

Width:  |  Height:  |  Size: 42 KiB

Before

Width:  |  Height:  |  Size: 72 KiB

After

Width:  |  Height:  |  Size: 72 KiB

Before

Width:  |  Height:  |  Size: 67 KiB

After

Width:  |  Height:  |  Size: 67 KiB

Before

Width:  |  Height:  |  Size: 99 KiB

After

Width:  |  Height:  |  Size: 99 KiB

Before

Width:  |  Height:  |  Size: 77 KiB

After

Width:  |  Height:  |  Size: 77 KiB

Before

Width:  |  Height:  |  Size: 55 KiB

After

Width:  |  Height:  |  Size: 55 KiB

Before

Width:  |  Height:  |  Size: 53 KiB

After

Width:  |  Height:  |  Size: 53 KiB

Before

Width:  |  Height:  |  Size: 72 KiB

After

Width:  |  Height:  |  Size: 72 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 198 KiB

After

Width:  |  Height:  |  Size: 228 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 152 KiB

After

Width:  |  Height:  |  Size: 228 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 136 KiB

After

Width:  |  Height:  |  Size: 243 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 507 KiB

After

Width:  |  Height:  |  Size: 604 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 340 KiB

After

Width:  |  Height:  |  Size: 412 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 209 KiB

After

Width:  |  Height:  |  Size: 227 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 186 KiB

After

Width:  |  Height:  |  Size: 266 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 226 KiB

After

Width:  |  Height:  |  Size: 266 KiB

+13 -13
View File
@@ -15,7 +15,7 @@ A summary of customization tips shared by Boris Cherny ([@bcherny](https://x.com
Boris Cherny highlighted that customizability is one of the things engineers love most about Claude Code — hooks, plugins, LSPs, MCPs, skills, effort, custom agents, status lines, output styles, and more. He shared 12 practical ways developers and teams are customizing their setups. Boris Cherny highlighted that customizability is one of the things engineers love most about Claude Code — hooks, plugins, LSPs, MCPs, skills, effort, custom agents, status lines, output styles, and more. He shared 12 practical ways developers and teams are customizing their setups.
<img src="assets/boris-feb-26/0.webp" alt="Boris Cherny intro tweet" width="50%" /> <a href="https://x.com/bcherny/status/2021699851499798911"><img src="assets/boris-12-feb-26/0.webp" alt="Boris Cherny intro tweet" width="50%" /></a>
--- ---
@@ -28,7 +28,7 @@ Set up your terminal for the best Claude Code experience:
- **Newlines**: If using Claude Code in an IDE terminal, Apple Terminal, Warp, or Alacritty, run `/terminal-setup` to enable shift+enter for newlines (so you don't need to type `\`) - **Newlines**: If using Claude Code in an IDE terminal, Apple Terminal, Warp, or Alacritty, run `/terminal-setup` to enable shift+enter for newlines (so you don't need to type `\`)
- **Vim mode**: Run `/vim` - **Vim mode**: Run `/vim`
<img src="assets/boris-feb-26/1.webp" alt="Configure your terminal" width="50%" /> <a href="https://x.com/bcherny/status/2021699859359883608"><img src="assets/boris-12-feb-26/1.webp" alt="Configure your terminal" width="50%" /></a>
--- ---
@@ -42,7 +42,7 @@ Run `/model` to pick your preferred effort level:
Boris's preference: High for everything. Boris's preference: High for everything.
<img src="assets/boris-feb-26/2.webp" alt="Adjust effort level" width="50%" /> <a href="https://x.com/bcherny/status/2021699860869902424"><img src="assets/boris-12-feb-26/2.webp" alt="Adjust effort level" width="50%" /></a>
--- ---
@@ -54,7 +54,7 @@ Install from the official Anthropic plugin marketplace, or create your own marke
Run `/plugin` to get started. Run `/plugin` to get started.
<img src="assets/boris-feb-26/3.webp" alt="Install Plugins, MCPs, and Skills" width="50%" /> <a href="https://x.com/bcherny/status/2021699862522364149"><img src="assets/boris-12-feb-26/3.webp" alt="Install Plugins, MCPs, and Skills" width="50%" /></a>
--- ---
@@ -66,7 +66,7 @@ You can also set the default agent for the main conversation using the `"agent"`
Run `/agents` to get started. Run `/agents` to get started.
<img src="assets/boris-feb-26/4.webp" alt="Create custom agents" width="50%" /> <a href="https://x.com/bcherny/status/2021700144039903699"><img src="assets/boris-12-feb-26/4.webp" alt="Create custom agents" width="50%" /></a>
--- ---
@@ -78,7 +78,7 @@ Out of the box, a small set of safe commands are pre-approved. To pre-approve mo
Full wildcard syntax is supported — e.g., `Bash(bun run *)` or `Edit(/docs/**)`. Full wildcard syntax is supported — e.g., `Bash(bun run *)` or `Edit(/docs/**)`.
<img src="assets/boris-feb-26/5.webp" alt="Pre-approve common permissions" width="50%" /> <a href="https://x.com/bcherny/status/2021700332292911228"><img src="assets/boris-12-feb-26/5.webp" alt="Pre-approve common permissions" width="50%" /></a>
--- ---
@@ -88,7 +88,7 @@ Opt into Claude Code's open source sandbox runtime to improve safety while reduc
Run `/sandbox` to enable it. Sandboxing runs on your machine and supports both file and network isolation. Run `/sandbox` to enable it. Sandboxing runs on your machine and supports both file and network isolation.
<img src="assets/boris-feb-26/6.webp" alt="Enable sandboxing" width="50%" /> <a href="https://x.com/bcherny/status/2021700506465579443"><img src="assets/boris-12-feb-26/6.webp" alt="Enable sandboxing" width="50%" /></a>
--- ---
@@ -98,7 +98,7 @@ Custom status lines show up right below the composer, displaying model, director
Every team member can have a different statusline. Use `/statusline` to have Claude generate one based on your `.bashrc`/`.zshrc`. Every team member can have a different statusline. Use `/statusline` to have Claude generate one based on your `.bashrc`/`.zshrc`.
<img src="assets/boris-feb-26/7.webp" alt="Add a status line" width="50%" /> <a href="https://x.com/bcherny/status/2021700784019452195"><img src="assets/boris-12-feb-26/7.webp" alt="Add a status line" width="50%" /></a>
--- ---
@@ -106,7 +106,7 @@ Every team member can have a different statusline. Use `/statusline` to have Cla
Every key binding in Claude Code is customizable. Run `/keybindings` to re-map any key. Settings live reload so you can see how it feels immediately. Every key binding in Claude Code is customizable. Run `/keybindings` to re-map any key. Settings live reload so you can see how it feels immediately.
<img src="assets/boris-feb-26/8.webp" alt="Customize your keybindings" width="50%" /> <a href="https://x.com/bcherny/status/2021700883873165435"><img src="assets/boris-12-feb-26/8.webp" alt="Customize your keybindings" width="50%" /></a>
--- ---
@@ -120,7 +120,7 @@ Hooks let you deterministically hook into Claude's lifecycle:
Ask Claude to add a hook to get started. Ask Claude to add a hook to get started.
<img src="assets/boris-feb-26/9.webp" alt="Set up hooks" width="50%" /> <a href="https://x.com/bcherny/status/2021701059253874861"><img src="assets/boris-12-feb-26/9.webp" alt="Set up hooks" width="50%" /></a>
--- ---
@@ -128,7 +128,7 @@ Ask Claude to add a hook to get started.
Customize your spinner verbs to add or replace the default list with your own verbs. Check the `settings.json` into source control to share verbs with your team. Customize your spinner verbs to add or replace the default list with your own verbs. Check the `settings.json` into source control to share verbs with your team.
<img src="assets/boris-feb-26/10.webp" alt="Customize your spinner verbs" width="50%" /> <a href="https://x.com/bcherny/status/2021701145023197516"><img src="assets/boris-12-feb-26/10.webp" alt="Customize your spinner verbs" width="50%" /></a>
--- ---
@@ -140,7 +140,7 @@ Run `/config` and set an output style to have Claude respond using a different t
- **Learning** — to have Claude coach you through making code changes - **Learning** — to have Claude coach you through making code changes
- **Custom** — create custom output styles to adjust Claude's voice - **Custom** — create custom output styles to adjust Claude's voice
<img src="assets/boris-feb-26/11.webp" alt="Use output styles" width="50%" /> <a href="https://x.com/bcherny/status/2021701379409273093"><img src="assets/boris-12-feb-26/11.webp" alt="Use output styles" width="50%" /></a>
--- ---
@@ -155,7 +155,7 @@ Claude Code works great out of the box, but when you do customize, check your `s
With 37 settings and 84 environment variables (use the `"env"` field in your `settings.json` to avoid wrapper scripts), there's a good chance any behavior you want is configurable. With 37 settings and 84 environment variables (use the `"env"` field in your `settings.json` to avoid wrapper scripts), there's a good chance any behavior you want is configurable.
<img src="assets/boris-feb-26/12.webp" alt="Customize all the things" width="50%" /> <a href="https://x.com/bcherny/status/2021701636075458648"><img src="assets/boris-12-feb-26/12.webp" alt="Customize all the things" width="50%" /></a>
--- ---
+14 -14
View File
@@ -15,7 +15,7 @@ A summary of setup tips shared by Boris Cherny ([@bcherny](https://x.com/bcherny
Boris shared his personal Claude Code setup, noting it's "surprisingly vanilla" — Claude Code works great out of the box, so he doesn't customize it much. There's no one correct way to use it: the team intentionally builds it so you can use, customize, and hack it however you like. Each person on the Claude Code team uses it very differently. Boris shared his personal Claude Code setup, noting it's "surprisingly vanilla" — Claude Code works great out of the box, so he doesn't customize it much. There's no one correct way to use it: the team intentionally builds it so you can use, customize, and hack it however you like. Each person on the Claude Code team uses it very differently.
<img src="assets/boris-3-jan-26/0.png" alt="Boris Cherny intro tweet" width="50%" /> <a href="https://x.com/bcherny/status/2007179832300581177"><img src="assets/boris-3-jan-26/0.png" alt="Boris Cherny intro tweet" width="50%" /></a>
--- ---
@@ -25,7 +25,7 @@ Run 5 Claudes in parallel in your terminal. Number your tabs 15, and use syst
See: [Terminal Setup Docs](https://code.claude.com/docs/en/terminal) See: [Terminal Setup Docs](https://code.claude.com/docs/en/terminal)
<img src="assets/boris-3-jan-26/1.png" alt="Run 5 Claudes in parallel" width="50%" /> <a href="https://x.com/bcherny/status/2007179833990885678"><img src="assets/boris-3-jan-26/1.png" alt="Run 5 Claudes in parallel" width="50%" /></a>
--- ---
@@ -33,7 +33,7 @@ See: [Terminal Setup Docs](https://code.claude.com/docs/en/terminal)
Run 510 Claudes on claude.ai/code in parallel with your local Claudes. Hand off local sessions to web sessions using `claude.ai/code`, manually kick off sessions in Chrome, and teleport back and forth. Run 510 Claudes on claude.ai/code in parallel with your local Claudes. Hand off local sessions to web sessions using `claude.ai/code`, manually kick off sessions in Chrome, and teleport back and forth.
<img src="assets/boris-3-jan-26/2.png" alt="claude.ai/code parallelism" width="50%" /> <a href="https://x.com/bcherny/status/2007179836704600237"><img src="assets/boris-3-jan-26/2.png" alt="claude.ai/code parallelism" width="50%" /></a>
--- ---
@@ -41,7 +41,7 @@ Run 510 Claudes on claude.ai/code in parallel with your local Claudes. Hand o
Use Opus 4.5 with thinking for everything. It's the best coding model Boris has ever used — even though it's bigger and slower than Sonnet, since you have to steer it less and it's better at tool use, it is almost always faster than using a smaller model in the end. Use Opus 4.5 with thinking for everything. It's the best coding model Boris has ever used — even though it's bigger and slower than Sonnet, since you have to steer it less and it's better at tool use, it is almost always faster than using a smaller model in the end.
<img src="assets/boris-3-jan-26/3.png" alt="Opus with thinking" width="50%" /> <a href="https://x.com/bcherny/status/2007179838864666847"><img src="assets/boris-3-jan-26/3.png" alt="Opus with thinking" width="50%" /></a>
--- ---
@@ -49,7 +49,7 @@ Use Opus 4.5 with thinking for everything. It's the best coding model Boris has
Share a single `CLAUDE.md` for the repo. Check it into git, and have the whole team contribute multiple times a week. Anytime Claude does something incorrectly, add it to the `CLAUDE.md` so Claude knows not to do it next time. Share a single `CLAUDE.md` for the repo. Check it into git, and have the whole team contribute multiple times a week. Anytime Claude does something incorrectly, add it to the `CLAUDE.md` so Claude knows not to do it next time.
<img src="assets/boris-3-jan-26/4.png" alt="Shared CLAUDE.md" width="50%" /> <a href="https://x.com/bcherny/status/2007179840848597422"><img src="assets/boris-3-jan-26/4.png" alt="Shared CLAUDE.md" width="50%" /></a>
--- ---
@@ -57,7 +57,7 @@ Share a single `CLAUDE.md` for the repo. Check it into git, and have the whole t
During code review, tag `@claude` on your coworkers' PRs to add something to the `CLAUDE.md` as part of the PR. Use the Claude Code GitHub action ([install-@hub-action](https://github.com/apps/claude)) for this — it's Boris's version of Compounding Engineering. During code review, tag `@claude` on your coworkers' PRs to add something to the `CLAUDE.md` as part of the PR. Use the Claude Code GitHub action ([install-@hub-action](https://github.com/apps/claude)) for this — it's Boris's version of Compounding Engineering.
<img src="assets/boris-3-jan-26/5.png" alt="Tag @claude on PRs" width="50%" /> <a href="https://x.com/bcherny/status/2007179842928947333"><img src="assets/boris-3-jan-26/5.png" alt="Tag @claude on PRs" width="50%" /></a>
--- ---
@@ -65,7 +65,7 @@ During code review, tag `@claude` on your coworkers' PRs to add something to the
Start most sessions in Plan mode (shift+tab twice). If the goal is to write a Pull Request, use Plan mode and go back and forth with Claude until you like its plan. From there, switch into auto-accept edits mode and Claude can usually 1-shot it. A good plan is really important. Start most sessions in Plan mode (shift+tab twice). If the goal is to write a Pull Request, use Plan mode and go back and forth with Claude until you like its plan. From there, switch into auto-accept edits mode and Claude can usually 1-shot it. A good plan is really important.
<img src="assets/boris-3-jan-26/6.png" alt="Plan mode" width="50%" /> <a href="https://x.com/bcherny/status/2007179845336527000"><img src="assets/boris-3-jan-26/6.png" alt="Plan mode" width="50%" /></a>
--- ---
@@ -75,7 +75,7 @@ Use slash commands for every "inner loop" workflow that you do many times a day.
Example: `/commit-push-pr` — Commit, push, and open a PR. Example: `/commit-push-pr` — Commit, push, and open a PR.
<img src="assets/boris-3-jan-26/7.png" alt="Slash commands" width="50%" /> <a href="https://x.com/bcherny/status/2007179847949500714"><img src="assets/boris-3-jan-26/7.png" alt="Slash commands" width="50%" /></a>
--- ---
@@ -85,7 +85,7 @@ Use a few subagents regularly: `code-simplifier` simplifies the code after Claud
Subagents live in `.claude/agents/`. Subagents live in `.claude/agents/`.
<img src="assets/boris-3-jan-26/8.png" alt="Subagents" width="50%" /> <a href="https://x.com/bcherny/status/2007179850139000872"><img src="assets/boris-3-jan-26/8.png" alt="Subagents" width="50%" /></a>
--- ---
@@ -107,7 +107,7 @@ Use a `PostToolUse` hook to format Claude's code. Claude usually generates well-
] ]
``` ```
<img src="assets/boris-3-jan-26/9.png" alt="PostToolUse hook for formatting" width="50%" /> <a href="https://x.com/bcherny/status/2007179852047335529"><img src="assets/boris-3-jan-26/9.png" alt="PostToolUse hook for formatting" width="50%" /></a>
--- ---
@@ -115,7 +115,7 @@ Use a `PostToolUse` hook to format Claude's code. Claude usually generates well-
Don't use `--dangerously-skip-permissions`. Instead, use `/permissions` to pre-allow common bash commands that you know are safe in your environment, to avoid unnecessary permission prompts. Most of these are checked into `.claude/settings.json` and shared with the team. Don't use `--dangerously-skip-permissions`. Instead, use `/permissions` to pre-allow common bash commands that you know are safe in your environment, to avoid unnecessary permission prompts. Most of these are checked into `.claude/settings.json` and shared with the team.
<img src="assets/boris-3-jan-26/10.png" alt="Pre-allow permissions" width="50%" /> <a href="https://x.com/bcherny/status/2007179854077407667"><img src="assets/boris-3-jan-26/10.png" alt="Pre-allow permissions" width="50%" /></a>
--- ---
@@ -123,7 +123,7 @@ Don't use `--dangerously-skip-permissions`. Instead, use `/permissions` to pre-a
Claude Code uses all your tools. It often searches and posts to Slack (via the MCP server), runs BigQuery queries to answer analytics questions (using `bq` CLI), grabs error logs from Sentry, etc. The Slack MCP configuration is checked into `.mcp.json` and shared with the team. Claude Code uses all your tools. It often searches and posts to Slack (via the MCP server), runs BigQuery queries to answer analytics questions (using `bq` CLI), grabs error logs from Sentry, etc. The Slack MCP configuration is checked into `.mcp.json` and shared with the team.
<img src="assets/boris-3-jan-26/11.png" alt="MCP tools" width="50%" /> <a href="https://x.com/bcherny/status/2007179856266789204"><img src="assets/boris-3-jan-26/11.png" alt="MCP tools" width="50%" /></a>
--- ---
@@ -131,7 +131,7 @@ Claude Code uses all your tools. It often searches and posts to Slack (via the M
For very long-running tasks, either (a) prompt Claude to verify its work with a background agent when it's done, (b) use an agent Stop hook to do that more deterministically, or (c) use the ralph-wiggum plugin (originally dreamt up by @GeoffreyHuntley). For very long-running tasks, either (a) prompt Claude to verify its work with a background agent when it's done, (b) use an agent Stop hook to do that more deterministically, or (c) use the ralph-wiggum plugin (originally dreamt up by @GeoffreyHuntley).
<img src="assets/boris-3-jan-26/12.png" alt="Long-running tasks verification" width="50%" /> <a href="https://x.com/bcherny/status/2007179858435281082"><img src="assets/boris-3-jan-26/12.png" alt="Long-running tasks verification" width="50%" /></a>
--- ---
@@ -141,7 +141,7 @@ Probably the most important thing to get great results out of Claude Code — gi
Claude tests every single change Boris lands. Claude tests every single change Boris lands.
<img src="assets/boris-3-jan-26/13.png" alt="Give Claude a way to verify" width="50%" /> <a href="https://x.com/bcherny/status/2007179861115511237"><img src="assets/boris-3-jan-26/13.png" alt="Give Claude a way to verify" width="50%" /></a>
--- ---