add Boris 13-tips (Jan 3) doc, rename tips files for consistency, and clean up README tips section

- Create tips/claude-boris-13-tips-03-jan-26.md from Boris's Jan 3 tweet thread (13 tips)
- Rename claude-boris-tips-feb-26.md → claude-boris-12-tips-12-feb-26.md for consistent naming
- Remove description hyperlinks for external-only URLs in Boris + Team section
- Add (Boris) attribution to Boris's tweets matching existing (Thariq) pattern
- Update all references in README.md and presentation/index.html

Co-Authored-By: Claude <noreply@anthropic.com>

README.md

@@ -151,17 +151,17 @@ claude
 
 ![Boris Cherny + Team](!/tags/boris-team.svg)
 
-- [Always use plan mode, give Claude a way to verify, use /code-review | 27/Dec/25](https://x.com/bcherny/status/2004711722926616680) ● [Tweet](https://x.com/bcherny/status/2004711722926616680)
-- [Ask Claude to interview you using AskUserQuestion tool (Thariq) | 28/Dec/25](https://x.com/trq212/status/2005315275026260309) ● [Tweet](https://x.com/trq212/status/2005315275026260309)
-- [Boris setup - 5 tips | 03/Jan/26](https://x.com/bcherny/status/2007179832300581177) ● [Tweet](https://x.com/bcherny/status/2007179832300581177)
-- [10 tips for using claude code by team itself | 01/Feb/26](https://x.com/bcherny/status/2017742741636321619) ● [Tweet](https://x.com/bcherny/status/2017742741636321619)
-- [12 ways how people are customizing their claudes | 12/Feb/26](tips/claude-boris-tips-feb-26.md) ● [Tweet](https://x.com/bcherny/status/2021699851499798911)
-- [Git Worktrees - 5 ways how boris is using | 21 Feb 2026](https://x.com/bcherny/status/2025007393290272904) ● [Tweet](https://x.com/bcherny/status/2025007393290272904)
-- [Seeing like an Agent - lessons from building Claude Code (Thariq) | 28 Feb 2026](https://x.com/trq212/status/2027463795355095314) ● [Tweet](https://x.com/trq212/status/2027463795355095314)
-- [AskUserQuestion + ASCII Markdowns (Thariq) | 28 Feb 2026](https://x.com/trq212/status/2027543858289250472) ● [Tweet](https://x.com/trq212/status/2027543858289250472)
-- [/loop — schedule recurring tasks for up to 3 days | 07 Mar 2026](https://x.com/bcherny/status/2030193932404150413) ● [Tweet](https://x.com/bcherny/status/2030193932404150413)
-- [Code Review — why fresh context windows catch bugs the original agent missed | 10 Mar 2026](https://x.com/bcherny/status/2031151689219321886) ● [Tweet](https://x.com/bcherny/status/2031151689219321886)
-- [/btw — side chain conversations while Claude works (Thariq) | 10 Mar 2026](https://x.com/trq212/status/2031506296697131352) ● [Tweet](https://x.com/trq212/status/2031506296697131352)
+- Always use plan mode, give Claude a way to verify, use /code-review (Boris) | 27/Dec/25 ● [Tweet](https://x.com/bcherny/status/2004711722926616680)
+- Ask Claude to interview you using AskUserQuestion tool (Thariq) | 28/Dec/25 ● [Tweet](https://x.com/trq212/status/2005315275026260309)
+- [How I use Claude Code — 13 tips from my surprisingly vanilla setup (Boris) | 03/Jan/26](tips/claude-boris-13-tips-03-jan-26.md) ● [Tweet](https://x.com/bcherny/status/2007179832300581177)
+- 10 tips for using claude code by team itself (Boris) | 01/Feb/26 ● [Tweet](https://x.com/bcherny/status/2017742741636321619)
+- [12 ways how people are customizing their claudes (Boris) | 12/Feb/26](tips/claude-boris-12-tips-12-feb-26.md) ● [Tweet](https://x.com/bcherny/status/2021699851499798911)
+- Git Worktrees - 5 ways how boris is using | 21 Feb 2026 ● [Tweet](https://x.com/bcherny/status/2025007393290272904)
+- Seeing like an Agent - lessons from building Claude Code (Thariq) | 28 Feb 2026 ● [Tweet](https://x.com/trq212/status/2027463795355095314)
+- AskUserQuestion + ASCII Markdowns (Thariq) | 28 Feb 2026 ● [Tweet](https://x.com/trq212/status/2027543858289250472)
+- /loop — schedule recurring tasks for up to 3 days (Boris) | 07 Mar 2026 ● [Tweet](https://x.com/bcherny/status/2030193932404150413)
+- Code Review — why fresh context windows catch bugs the original agent missed (Boris) | 10 Mar 2026 ● [Tweet](https://x.com/bcherny/status/2031151689219321886)
+- /btw — side chain conversations while Claude works (Thariq) | 10 Mar 2026 ● [Tweet](https://x.com/trq212/status/2031506296697131352)
 
 ## ☠️ STARTUPS / BUSINESSES
 

presentation/index.html

@@ -1653,7 +1653,7 @@ managed-settings.json              <span class="comment"># Organization policy (
         <h1>Resources</h1>
         <div class="use-cases">
             <div class="use-case-item"><span class="use-case-icon">&#128214;</span><div class="use-case-text"><strong>Claude Code Docs</strong><span>code.claude.com/docs/en</span></div></div>
-            <div class="use-case-item"><span class="use-case-icon">&#128161;</span><div class="use-case-text"><strong>Boris Cherny's 12 Tips</strong><span>tips/claude-boris-tips-feb-26.md</span></div></div>
+            <div class="use-case-item"><span class="use-case-icon">&#128161;</span><div class="use-case-text"><strong>Boris Cherny's 12 Tips</strong><span>tips/claude-boris-12-tips-12-feb-26.md</span></div></div>
             <div class="use-case-item"><span class="use-case-icon">&#127959;</span><div class="use-case-text"><strong>This Repository</strong><span>Working examples of skills, agents, hooks, and the Command &rarr; Agent &rarr; Skills pattern</span></div></div>
             <div class="use-case-item"><span class="use-case-icon">&#128295;</span><div class="use-case-text"><strong>Claude Code Voice Hooks</strong><span>github.com/shanraisshan/claude-code-voice-hooks</span></div></div>
         </div>

tips/claude-boris-13-tips-03-jan-26.md

@@ -0,0 +1,150 @@
+# How I Use Claude Code — 13 Tips from Boris Cherny
+
+A summary of setup tips shared by Boris Cherny ([@bcherny](https://x.com/bcherny)), creator of Claude Code, on January 3, 2026.
+
+<table width="100%">
+<tr>
+<td><a href="../">← Back to Claude Code Best Practice</a></td>
+<td align="right"><img src="../!/claude-jumping.svg" alt="Claude" width="60" /></td>
+</tr>
+</table>
+
+---
+
+## Context
+
+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%" />
+
+---
+
+## 1/ Run 5 Claudes in Parallel
+
+Run 5 Claudes in parallel in your terminal. Number your tabs 1–5, and use system notifications to know when a Claude needs input.
+
+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%" />
+
+---
+
+## 2/ Use claude.ai/code for Even More Parallelism
+
+Run 5–10 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%" />
+
+---
+
+## 3/ Use Opus with Thinking for Everything
+
+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%" />
+
+---
+
+## 4/ Share a Single CLAUDE.md with Your Team
+
+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%" />
+
+---
+
+## 5/ Tag @claude on PRs to Update CLAUDE.md
+
+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%" />
+
+---
+
+## 6/ Start Most Sessions in Plan Mode
+
+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%" />
+
+---
+
+## 7/ Use Slash Commands for Inner Loop Workflows
+
+Use slash commands for every "inner loop" workflow that you do many times a day. This saves you from repeated prompting, and makes it so Claude can use these workflows too. Commands are checked into git and live in `.claude/commands/`.
+
+Example: `/commit-push-pr` — Commit, push, and open a PR.
+
+<img src="assets/boris-3-jan-26/7.png" alt="Slash commands" width="50%" />
+
+---
+
+## 8/ Use Subagents to Automate Common Workflows
+
+Use a few subagents regularly: `code-simplifier` simplifies the code after Claude is done working, `verify-app` has detailed instructions for testing Claude Code end to end, and so on. Think of subagents as automating the most common workflows — similar to slash commands.
+
+Subagents live in `.claude/agents/`.
+
+<img src="assets/boris-3-jan-26/8.png" alt="Subagents" width="50%" />
+
+---
+
+## 9/ Use a PostToolUse Hook to Auto-Format Code
+
+Use a `PostToolUse` hook to format Claude's code. Claude usually generates well-formatted code out of the box, and the hook handles the last 10% to avoid formatting errors in CI later.
+
+```json
+"PostToolUse": [
+  {
+    "matcher": "Write|Edit",
+    "hooks": [
+      {
+        "type": "command",
+        "command": "bun run format || true"
+      }
+    ]
+  }
+]
+```
+
+<img src="assets/boris-3-jan-26/9.png" alt="PostToolUse hook for formatting" width="50%" />
+
+---
+
+## 10/ Pre-allow Permissions Instead of --dangerously-skip-permissions
+
+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%" />
+
+---
+
+## 11/ Let Claude Use All Your Tools via MCP
+
+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%" />
+
+---
+
+## 12/ Verify Long-Running Tasks with Background Agents
+
+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%" />
+
+---
+
+## 13/ Give Claude a Way to Verify Its Work
+
+Probably the most important thing to get great results out of Claude Code — give Claude a way to verify its work. If Claude has that feedback loop, it will 2–3x the quality of the final result.
+
+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%" />
+
+---
+
+## Sources
+
+- [Boris Cherny (@bcherny) on X — January 3, 2026](https://x.com/bcherny/status/2007179832300581177)